Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
Open accessThe DOI matches its Crossref record; 157 of the 158 references it cites were found in a registry or an index, and 1 are not checked yet; 29 of the 52 sources its claims cite were checked for support.
Abstract
Abstract Do large language models (LLMs) know the law? LLMs are increasingly being used to augment legal practice, education, and research, yet their revolutionary potential is threatened by the presence of “hallucinations”—textual output that is not consistent with legal facts. We present the first systematic evidence of these hallucinations in public-facing LLMs, documenting trends across jurisdictions, courts, time periods, and cases. Using OpenAI’s ChatGPT 4 and other public models, we show that LLMs hallucinate at least 58% of the time, struggle to predict their own hallucinations, and often uncritically accept users’ incorrect legal assumptions. We conclude by cautioning against the rapid and unsupervised integration of popular LLMs into legal tasks, and we develop a typology of legal hallucinations to guide future research in this area.
Verified 2026-11-19 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This paper provides the first systematic evidence that public LLMs frequently hallucinate on verifiable questions about U.S. federal case law, with hallucination rates ranging from 58% for ChatGPT 4 to 88% for Llama 2. It also documents correlates of hallucination and two additional failure modes: susceptibility to false legal premises and poor calibration about their own accuracy.
Key findings
- Hallucinations are widespread across all tested LLMs on direct, verifiable federal case questions: ChatGPT 4 hallucinates 58% of the time, while Llama 2 hallucinates 88%; GPT 4 performs best overall, followed by GPT 3.5, PaLM 2, and Llama 2.
- Hallucination rates increase with task complexity and vary by court hierarchy, jurisdiction, case prominence, and case year. For reference-free high-complexity tasks, the reported rates are lower bounds: at least 49% for factual background and procedural posture, at least 59% for core legal question, and at least 63% for central holding; doctrinal agreement is near 0.5, little better than random guessing.
- LLMs often accept false legal premises: on the false dissent premise, GPT 4 hallucinates 0.691 at SCOTUS and 0.842 at USCOA; on the false overruling premise, GPT 4 hallucinates 0.531, GPT 3.5 0.821, PaLM 2 1.000, and Llama 2 0.027. Llama 2’s low contra-factual rate reflects its tendency to reject premises, which harms its performance on other tasks such as Existence.
- Calibration is poor and systematically overconfident: pooled expected calibration error is 0.057 for PaLM 2, 0.099 for GPT 3.5, 0.190 for GPT 4, and 0.421 for Llama 2. Although GPT 4 has the lowest raw hallucination rate, it is less calibrated than PaLM 2 and GPT 3.5.
Methods
- The authors develop 14 legal knowledge QA tasks grouped into low, moderate, and high complexity. The first nine are reference-based and scored against metadata from the Caselaw Access Project, Supreme Court Database, Appeals Courts Database Project, Library of Congress, and Shepard’s Citations; the final five are reference-free and detected via self-contradiction between repeated stochastic responses, using GPT 4 for contradiction labeling.
- They draw 5,000 cases each from SCOTUS, USCOA, and USDC using stratified random sampling, then query four off-the-shelf LLMs—OpenAI ChatGPT 4, OpenAI ChatGPT 3.5, Google PaLM 2, and Meta Llama 2—under zero-shot and three-shot prompting. They execute more than 800,000 queries, over 200,000 per LLM, generally at temperature 0 for reference-based tasks.
- Analyses estimate population-level hallucination rates, heterogeneity across task, court, jurisdiction, prominence, and year, plus contra-factual bias and expected calibration error.
Limitations
- The paper states that reference-free hallucination rates are only lower bounds because self-contradiction guarantees hallucination but logically consonant answers may still be false; it also cannot capture repeated incorrect answers as hallucinations, and notes that the SCOTUS Subsequent history estimate likely understates hallucination by a larger margin.
- The paper states that it relies on GPT 4 for contradiction detection, though it validates this with human intercoder reliability (Cohen’s κ: Coder 1 vs. GPT 4 = 0.87; Coder 2 vs. GPT 4 = 0.77; Coder 1 vs. Coder 2 = 0.79). It also notes that closed-source models do not expose conditional probabilities, so calibration is estimated by sampling at temperature 1, and that ex post temperature scaling improves but does not fully solve calibration.
- Evident from the text: the study tests specific public model versions available at the time, so results may not generalize to newer LLMs or to retrieval-augmented, fine-tuned, or proprietary legal systems; the tasks are limited to published federal case law and to metadata available for constructing ground truth.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
16 Valid · 5 Not valid · 9 Not checked · 105 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“since hallucinations of some kind are generally inevitable at the token level (Kalai and Vempala 2023; Xu, Jain, and Kankanhalli 2024)”
What the sources say
- Disputedcites Kalai and Vempala 2023 matched to “Calibrated Language Models Must Hallucinate” (2023)Experimental — accuracy not yet measured
The Introduction (p. 1) explicitly says the paper's lower bounds for calibrated predictors of facts should not be taken to mean hallucination is inevitable. The discussion on p. 2 distinguishes its semantic-level calibration from token-level calibration, so it does not establish inevitability at the token level. (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
- Partly supportedcites Xu, Jain, and Kankanhalli 2024 matched to “Hallucination is Inevitable: An Innate Limitation of Large Language Models” (2024) sourceExperimental — accuracy not yet measured
Section 3.2 (p. 7) concludes that LLM hallucination cannot be eliminated, supporting the inevitability claim. But Section 2.1 (p. 2) describes token-by-token generation, while the paper defines hallucination by comparing complete output strings with ground truth; it does not establish inevitability specifically at the token level. (LLM, conf=0.85)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“as Kalai and Vempala (2023) show, LMs that assign a positive probability to every response token must hallucinate at least some of the time”
What the sources say
- Supportedcites Kalai and Vempala (2023) matched to “Calibrated Language Models Must Hallucinate” (2023)
The Introduction (p. 1) explicitly says that an LM predicting every string with positive probability will necessarily hallucinate with positive probability. This supports the claim's paraphrase that such hallucination occurs at least some of the time. (LLM, conf=0.93)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Xu, Jain, and Kankanhalli (2024) agree, arguing that 'hallucination is inevitable for any computable LLM, regardless of model architecture, learning algorithms, prompting techniques, or training data.'”
What the sources say
- Supportedcites Xu, Jain, and Kankanhalli (2024) matched to “Hallucination is Inevitable: An Innate Limitation of Large Language Models” (2024) source
The Introduction (p. 2) states the attributed claim nearly verbatim. It frames the result under the paper’s formal definition of hallucination and says it applies to real-world LLMs. (LLM, conf=0.95)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“increased reliance on LLMs also has the potential to produce a kind of legal monoculture (Creel and Hellman 2022; Kleinberg and Raghavan 2021), with users being fed information from only a limited subset of judicial sources that elide many of the deeper nuances of the law.”
What the sources say
- Partly supportedcites Creel and Hellman 2022 matched to “The Algorithmic Leviathan: Arbitrariness, Fairness, and Opportunity in Algorithmic Decision-Making Systems” (2022) sourceExperimental — accuracy not yet measured
Section 3.a, “Why arbitrariness at scale arises” (page unavailable), says that reliance on similar datasets can standardize different algorithms and produce uniform outcomes. That supports the general concern about algorithmic monoculture, but the paper does not address LLMs feeding users a limited subset of judicial sources or eliding nuances of law. (LLM, conf=0.84)
- Partly supportedcites Kleinberg and Raghavan 2021 matched to “Algorithmic monoculture and social welfare” (2021) sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes algorithmic curation making choices more homogeneous, and the Conclusion (p. 12) says shared evaluations can cause valuable options to be overlooked. Those passages support the general possibility of monoculture, but the paper examines algorithmic screening, not LLMs or whether users receive a limited subset of judicial sources that omits legal nuance. (LLM, conf=0.87)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“the problem of legal hallucination has so far only been studied in closed-domain applications, such as when a model is used to summarize the content of a given judicial opinion (Deroy, Ghosh, and Ghosh 2023; Feijo and Moreira 2023) or to synthesize provided legal text (Savelka et al. 2023)”
What the sources say
- Partly supportedcites Deroy, Ghosh, and Ghosh 2023 matched to “How Ready are Pre-trained Abstractive Models and LLMs for Legal Case Judgement Summarization?” (2023) sourceExperimental — accuracy not yet measured
The Abstract describes a study of hallucinations in summaries generated from Indian court case judgments, supporting this paper as an example of a closed-domain legal application. The Introduction’s “Novelty of this work” section says that, to the authors’ knowledge, hallucination had not previously been studied in legal summarization. Neither passage establishes the broader claim that legal hallucination had only been studied in closed-domain applications. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites Feijo and Moreira 2023 matched to “Improving Abstractive Summarization of Legal Rulings through Textual Entailment” (2023) source
- Partly supportedcites Savelka et al. 2023 matched to “Explaining Legal Concepts with Augmented Large Language Models (GPT-4)” (2023) sourceExperimental — accuracy not yet measured
The Proposed Method (pp. 6–7) describes an augmented setup that synthesizes retrieved case-law sentences into an explanation, supporting the example attributed to Savelka et al. But it also studies a baseline that generates explanations without those retrieved sentences, and the Conclusions (p. 13) report hallucinated case-law citations in that baseline. The paper therefore does not support the claim that legal hallucination had only been studied in closed-domain applications. (LLM, conf=0.87)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
60 more claims · 3 with their cited sources checked
Create a free account to see all 135 claims and to verify the 1 reference still open.
- Probably not a substantial claim. 42
- It may state two separate claims as one. 44
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In high-stake domains such as legal consultation or scientific research, these hallucinations can lead to severe misjudgments and erode user trust [190,191].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [190]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent research has shown that leading language models – ChatGPT, Deepseek, Grok, PaLM, Claude, Qwen, and Llama – were on average producing hallucinations in 75 % of the cases (Dahl et al., 2024), with many users unaware of this prevalence (Williamson & Prybutok, 2024).”
From If ChatGPT can do it, where is my creativity? generative AI boosts performance but diminishes experience in creative writing (2025) · cites this paper as Dahl et al., 2024
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Dahl et al. [7] showed that even models with high bar exam scores systematically fabricate case references when applied to real legal tasks.”
From Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs (2026) · cites this paper as [7]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“a confident legal summary can make uncertain advice feel authoritative [93]”
From Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration (2026) · cites this paper as [93]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Previous work has found that general- purpose LLMs hallucinate on legal queries on average between 58% and 82% of the time (Dahl et al. 2024).”
From Hallucination‐Free? Assessing the Reliability of Leading AI Legal Research Tools (2025) · cites this paper as Dahl et al. 2024
Experimental — accuracy not yet measured
10 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ E.1 Fake Case Existence Task · p. 61
“GPT 4 and Llama 2, on the other hand, appear immune from this behavior, but recall from Table 2 that this is just bias in the opposite direction: they simply prefer to deny the existence of any case, real or fake.”
§ 6 Discussion · p. 38
“| Existence | Zero-shot | 0.204 (0.006) | 0.004 (0.001) | 0.054 (0.003) | 0.303 (0.006)”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 5.1.2 Hallucinations Vary by Court · p. 24
“We find that across all tasks and all LLMs, hallucinations are lowest in the highest levels of the judiciary, and vice-versa (Figure 3).”
§ 6 Discussion · p. 38
“| Citation | Few-shot | 0.689 (0.007) | 0.641 (0.007) | 0.833 (0.005) | 0.953 (0.003) | 0.468 (0.007)”
Citations
Cites
The Measurement of Observer Agreement for Categorical Data
Landis, J. R., & Koch, G. G. (1977) · Biometrics · doi:10.2307/2529310 · Cited by 81,148
A Coefficient of Agreement for Nominal Scales
Cohen, J. (1960) · Educational and Psychological Measurement · doi:10.1177/001316446002000104 · Cited by 42,398
Tversky, A., & Kahneman, D. (1974) · Science · doi:10.1126/science.185.4157.1124 · Cited by 28,810 · cited 1×
“…(the tendency of an LLM to agree with a user’s preferences or beliefs, even when the LLM would reject the belief as wrong without the user’s prompting; Sharma et al., 2023; Wei et al., 2023) or general cognitive error (Tversky and Kahneman, 1974; Jones and Steinhardt, 2022; Suri et al., 2023).”
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435
Barocas, S., & Selbst, A. D. (2014) · doi:10.2139/ssrn.2477899 · Cited by 3,048
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Self-citationLlama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Research works printed but not linked: 10
- Ambrogi, Bob. 2023. 'As Allen & Overy Deploys GPT-based Legal App Harvey Firmwide, Founders Say Other Firms Will Soon Follow.' LawSites.
- Chien, Colleen V., Miriam Kim, Raj Akhil, and Rohit Rathish. 2024. 'How Generative AI Can Help Address the Access to Justice Gap Through the Courts.' Loyola of Los Angeles Law Review, forthcoming.
- Draper, Chris, and Nicky Gillibrand. 2023. 'The Potential for Jurisdictional Challenges to AI or LLM Training Datasets.' In Proceedings of the ICAIL 2023 Workshop on Artificial Intelligence for Access to Justice. Braga, Portugal: CEUR Workshop Proceedings.
- Dworkin, Ronald. 1986. Law's Empire. Cambridge, MA: Harvard University Press.
- Luft, Joseph, and Harrington Ingham. 1955. 'The Johari Window as a Graphic Model of Interpersonal Awareness.' In Proceedings of the Western Training Laboratory in Group Development. University of California, Los Angeles, Extension Office.
- Mayson, Sandra G. 2019. 'Bias In, Bias Out.' The Yale Law Journal 128 (8): 2122-2473.
- Romoser, James. 2023. 'No, Ruth Bader Ginsburg Did Not Dissent in Obergefell - and Other Things ChatGPT Gets Wrong about the Supreme Court.' SCOTUSblog.
- Simshaw, Drew. 2022. 'Access to A.I. Justice: Avoiding an Inequitable Two-Tiered System of Legal Services.' Yale Journal of Law & Technology 24:150-226.
- Tan, Jinzhe, Hannes Westermann, and Karim Benyekhlef. 2023. 'ChatGPT as an Artificial Lawyer?' In Proceedings of the ICAIL 2023 Workshop on Artificial Intelligence for Access to Justice. Braga, Portugal: CEUR Workshop Proceedings.
- Weiser, Benjamin. 2023. 'Here's What Happens When Your Lawyer Uses ChatGPT.' The New York Times.
Cited by
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 671
“In high-stake domains such as legal consultation or scientific research, these hallucinations can lead to severe misjudgments and erode user trust [190,191].”
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · arXiv · doi:10.48550/arxiv.2505.10468 · Cited by 295
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186
Hallucination‐Free? Assessing the Reliability of Leading AI Legal Research Tools
Magesh, V., Surani, F., Dahl, M., Suzgun, M., Manning, C. D., & Ho, D. E. (2025) · Journal of Empirical Legal Studies · doi:10.1111/jels.12413 · Cited by 182
Self-citationGenerative AI in EU law: Liability, privacy, intellectual property, and cybersecurity
Novelli, C., Casolari, F., Hacker, P., Spedicato, G., & Floridi, L. (2024) · Computer Law & Security Review · doi:10.1016/j.clsr.2024.106066 · Cited by 124
Generalization bias in large language model summarization of scientific research
Peters, U., & Chin-Yee, B. (2025) · Royal Society Open Science · doi:10.1098/rsos.241776 · Cited by 126
Roberts, J., Baker, M., & Andrew, J. (2024) · Critical Perspectives on Accounting · doi:10.1016/j.cpa.2024.102722 · Cited by 132
Ariai, F., Mackenzie, J., & Demartini, G. (2025) · ACM Computing Surveys · doi:10.1145/3777009 · Cited by 278
Hindi, M., Mohammed, L., Maaz, O., & Alwarafy, A. (2025) · IEEE Access · doi:10.1109/access.2025.3550145 · Cited by 142
“However, in legal applications, LLMs have exhibited high hallucination rates [10].”
Do large language models have a legal duty to tell the truth?
Wachter, S., Mittelstadt, B., & Russell, C. (2024) · Royal Society Open Science · doi:10.1098/rsos.240197 · Cited by 66
An automated framework for assessing how well LLMs cite relevant medical references
Wu, K., Wu, E., Wei, K., Zhang, A., Casasola, A., Nguyen, T., Riantawan, S., Shi, P., Ho, D., & Zou, J. (2025) · Nature Communications · doi:10.1038/s41467-025-58551-6 · Cited by 72
Self-citationKim, S. S. Y., Vaughan, J. W., Liao, Q. V., Lombrozo, T., & Russakovsky, O. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714020 · Cited by 58
“However, the responses produced by LLMs are often inaccurate, sometimes in subtle ways [27, 51, 103, 108].”
Generative Ai in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity
Novelli, C., Casolari, F., Hacker, P., Spedicato, G., & Floridi, L. (2024) · doi:10.2139/ssrn.4821952 · Cited by 57
Mei, P., Brewis, D. N., Nwaiwu, F., Sumanathilaka, D., Alva-Manchego, F., & Demaree-Cotton, J. (2025) · Computers in Human Behavior: Artificial Humans · doi:10.1016/j.chbah.2025.100140 · Cited by 50
Language agents achieve superhuman synthesis of scientific knowledge
Skarlinski, M. D., Cox, S., Laurent, J. M., Braza, J. D., Hinks, M., Hammerling, M. J., Ponnapati, M., Rodriques, S. G., & White, A. D. (2024) · arXiv · doi:10.48550/arxiv.2409.13740 · Cited by 49
“Secondly, science requires extreme attention to detail, and LLMs can overlook or misuse details when faced with challenging reasoning problems 5 .”
BackgroundPeykani, P., Ramezanlou, F., Tănăsescu, C. R., & Ghanidel, S. (2025) · Applied Sciences · doi:10.3390/app15148103 · Cited by 83
Generative AI risks and resilience: How users adapt to hallucination and privacy challenges
Lee, C., Kim, J., Lim, J. S., & Shin, D. (2025) · Telematics and Informatics Reports · doi:10.1016/j.teler.2025.100221 · Cited by 73
Enabling large language models for real-world materials discovery
Miret, S., & Krishnan, N. M. A. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01058-y · Cited by 165
Large language models hallucination: A comprehensive survey
Alansari, A., & Luqman, H. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100970 · Cited by 258
Medical Hallucinations in Foundation Models and Their Impact on Healthcare
Kim, Y., Jeong, H., Chen, S., Li, S. S., Park, C., Lu, M., Alhamoud, K., Mun, J., Grau, C., Jung, M., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.05777 · Cited by 33
How do judges use large language models? Evidence from Shenzhen
Liu, J. Z., & Li, X. (2024) · The Journal of Legal Analysis · doi:10.1093/jla/laae009 · Cited by 54
Examining the ethical and sustainability challenges of legal education’s AI revolution
Balan, A. (2024) · International Journal of the Legal Profession · doi:10.1080/09695958.2024.2421179 · Cited by 51
“…like Dahl and others ’ ongoing research on the use of large language models (LLMs) as legal analytic tools highlight the continuing unreliability of such AI, particularly in relation to legal hallucinations (responses from these models that are not consistent with legal facts) (Dahl et al. 2024).”
Emerging trends: a gentle introduction to RAG
Church, K., Sun, J., Yue, R., Vickers, P., Saba, W., & Chandrasekar, R. (2024) · Natural Language Engineering · doi:10.1017/s1351324924000044 · Cited by 45
Wahidur, R. S. M., Kim, S., Choi, H., Bhatti, D. S., & Lee, H.-N. (2025) · IEEE Access · doi:10.1109/access.2025.3542125 · Cited by 57
“Research indicates that general-purpose LLMs frequently hallucinate when responding to legal queries, with an average occurrence rate between 58% and 82% [9].”
Secret Use of Large Language Model (LLM)
Zhang, Z., Shen, C., Yao, B., Wang, D., & Li, T. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711061 · Cited by 48
Bajohr, H. (2024) · Poetics Today · doi:10.1215/03335372-11092990 · Cited by 40
“A recent Stanford study found that — even though the model has allegedly passed the bar exam approaching the ninetieth percentile (Katz et al. 2023) — ChatGPT still produces hallucinations 69 percent of the time when it comes to legal writing (Dahl et al. 2024).”
MethodHarašta, J., Novotná, T., & Šavelka, J. (2024) · Artificial Intelligence and Law · doi:10.1007/s10506-024-09422-w · Cited by 47
SciSciGPT: advancing human–AI collaboration in the science of science
Shao, E., Wang, Y., Qian, Y., Pan, Z., Liu, H., & Wang, D. (2025) · Nature Computational Science · doi:10.1038/s43588-025-00906-6 · Cited by 76
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
Rao, D., Wong, E., & Callison-Burch, C. (2026) · arXiv · doi:10.48550/arxiv.2604.03173 · Cited by 16
A Large Language Model Agent Based Legal Assistant for Governance Applications
Mamalis, M. E., Kalampokis, E., Fitsilis, F., Theodorakopoulos, G., & Tarabanis, K. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70274-7_18 · Cited by 31
Schneiders, E., Seabrooke, T., Krook, J., Hyde, R., Leesakul, N., Clos, J., & Fischer, J. E. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713470 · Cited by 43
Judge AI: Assessing Large Language Models in Judicial Decision-MakingPreprint
Posner, E. A., & Saran, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5098708 · Cited by 15
Simplifying software compliance: AI technologies in drafting technical documentation for the AI Act
Sovrano, F., Hine, E., Anzolut, S., & Bacchelli, A. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10645-x · Cited by 35
“This issue is compounded by its limited understanding of meaning, particularly in legal contexts, as highlighted by Dahl et al. (2024) and Bender and Koller (2020).”
From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs
Kazlaris, I., Antoniou, E., Diamantaras, K., & Bratsas, C. (2025) · doi:10.20944/preprints202508.1942.v1 · Cited by 13
A Comprehensive Survey on Legal Summarization: Challenges and Future Directions
Akter, M., Çano, E., Weber, E., Dobler, D., & Habernal, I. (2025) · ACM Computing Surveys · doi:10.1145/3776586 · Cited by 47
“First, possible hallucinations in summarized texts are inevitable, as LLMs generate legal texts that are inconsistent with the legal doctrine or provide an imprecise interpretation of the law [25, 88].”
From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMs
Kazlaris, I., Antoniou, E. N., Diamantaras, K., & Bratsas, C. (2025) · AI · doi:10.3390/ai6100260 · Cited by 35
On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations
Sadowski, A., & Chudziak, J. A. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761057 · Cited by 27
“Forlegal reasoning, LLMs show promise but face significant challenges requiring consistent rule application and explainable outcomes [12].”
A Survey of Lay People's Willingness to Generate Legal Advice using Large Language Models (LLMs)
Seabrooke, T., Schneiders, E., Dowthwaite, L., Krook, J., Leesakul, N., Clos, J., Maior, H. A., & Fischer, J. E. (2024) · International Symposium on Trustworthy Autonomous Systems (TAS) · doi:10.1145/3686038.3686043 · Cited by 24
“They cautioned lawyers to be very careful when using LLMs such as ChatGPT, because of their capacity to generate false and misleading content, i.e., hallucinations [4, 17].”
The Possibility of Applying Artificial Intelligence in the Delivery of Justice by Courts
Tamošiūnienė, E., Terebeiza, Ž., & Doržinkevič, A. (2024) · Baltic Journal of Law & Politics · doi:10.2478/bjlp-2024-0010 · Cited by 10
Han, Z., Battaglia, F., Mansuria, K., Heyman, Y., & Terlecky, S. R. (2025) · AI · doi:10.3390/ai6010012 · Cited by 18
Interacting with AI at Work: Perceptions and Opportunities from the UK Judiciary
Solovey, E., Flanagan, B., & Chen, D. L. (2025) · Annual Symposium on Human-Computer Interaction for Work (CHIWORK) · doi:10.1145/3729176.3729192 · Cited by 14
Παπαδόπουλος, Θ., Alexopoulos, C., & Charalabidis, Y. K. (2025) · Frontiers in Political Science · doi:10.3389/fpos.2025.1601440 · Cited by 15
Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach
Sadowski, A., & Chudziak, J. A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.337 · Cited by 20
“Third, the black-box nature of neural architectures makes reasoning paths opaque [9], limiting human oversight and preventing verification of the logical steps leading to a conclusion.”
InfluentialThe Factuality of Large Language Models in the Legal Domain
Hamdani, R. E., Bonald, T., Malliaros, F. D., Holzenberger, N., & Suchanek, F. M. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679961 · Cited by 25
“The legal domain is particularly sensitive to hallucinations, as incorrect information can lead to harmful decisions [12].”
Han, Z., Battaglia, F., & Terlecky, S. R. (2024) · The Innovation Medicine · doi:10.59717/j.xinn-med.2024.100065 · Cited by 7
Impact of high data quality on LLM hallucinations
Gautam, A. R. (2025) · International Journal of Computer Applications · doi:10.5120/ijca2025924909 · Cited by 6
AI-driven design: powered by large language model and intelligent computation
Sa, G., Li, Z., Liu, Z., & Tan, J. (2025) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/adea23 · Cited by 8
Legal knowledge infusion for large language models: A survey
Liu, Q., Yu, H., Wang, Q., Xu, Q., Li, J., Zou, Z., Mao, R., & Cambria, E. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103426 · Cited by 15
DIKWP Semantic Judicial Reasoning: A Framework for Semantic Justice in AI and Law
Mei, Y., & Duan, Y. (2025) · Information · doi:10.3390/info16080640 · Cited by 6
Iyidogan, E., & Özkes, A. (2025) · Economics Letters · doi:10.1016/j.econlet.2025.112520 · Cited by 10
“…a discrete menu of models that differ markedly in both their per-query price and their output quality, measured for instance by the baseline hallucination rate, the rate at which the model falsely claims to have performed an action or generated a correct response (Canayaz, 2025; Dahl et al., 2024).”
A Reusable Prompting Framework for Applying Large Language Models to Legal Tasks
Sriram, S., Vijayaraj, N., Krishna, G. R., Bhanu, S. V., Choudhary, G., & Murugan, T. (2026) · IEEE Access · doi:10.1109/access.2026.3650941 · Cited by 11
“Dahl et al. [28] found that the rate of hallucination in legal fact questions varied between 58% and 88% in various jurisdictions and types of courts.”
Challenges for generative AI in legal reasoning
Linna, E., & Linna, T. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-00902-3 · Cited by 25
“Evidence evaluation involves piecing together fragments of information with no authoritative source of truth available for the LLM’s reference, increasing the risk of hallucinations [30].”
On the Explainability of Financial Robo-Advice Systems
Vilone, G., Sovrano, F., & Lognoul, M. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63803-9_12 · Cited by 9
Application of Generative AI to Derive Insight from Supply Chain & Logistics Contracts
Singh, A. P., Jia, T., Nalagatla, V., Cunningham, B., & Siwani, T. (2024) · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC) · doi:10.2118/222932-ms · Cited by 6
Application of Generative Artificial Intelligence in Dyslipidemia Care
Ahn, J., & Kim, B.-K. (2025) · Journal of Lipid and Atherosclerosis · doi:10.12997/jla.2025.14.1.77 · Cited by 8
Legal large language models (LLMs): legal dynamos or “fancifully packaged ChatGPT”?
Ogunde, F. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00167-8 · Cited by 6
A Layered Multi-Expert Framework for Long-Context Mental Health Assessments
Tang, J., Guo, Q., Sun, W., & Shang, Y. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00080 · Cited by 5
“Second, long and complex transcripts —such as multi-turn interviews or narrative case studies—can overwhelm advanced models, leading to hallucinations or inconsistencies [6], [7].”
Li, Y., Fu, X., Verma, G., Buitelaar, P., & Liu, M. (2025) · arXiv · doi:10.48550/arxiv.2510.24476 · Cited by 4
“This phenomenon seriously affects the reliability and controllability of LLMs, especially in high-stakes domains such as medicine, law, and finance, where high accuracy, consistency, verifiability, and traceability are critical [32, 50].”
Abedi, F., Rajabifard, A., & Shojaei, D. (2025) · Computer law & security review · doi:10.1016/j.clsr.2025.106194 · Cited by 4
LegalAI Research in LLM Era: Data, Modeling and Evaluation
Chi, X., Wang, W., Zhang, Z., Li, A., Huang, Y., Wu, Y., Kuang, K., Sun, C., Liu, X., Wu, F., et al. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11514-9 · Cited by 11
Hassani, S., Sabetzadeh, M., & Amyot, D. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108122 · Cited by 5
FEASIBILITY OF USING LOW-PARAMETER LOCAL LLMS IN ANSWERING QUESTIONS FROM ENTERPRISE KNOWLEDGE BASE
Badurowicz, M., Skulimowski, S. P., & LASKOWSKI, M. (2024) · Applied Computer Science · doi:10.35784/acs-2024-46 · Cited by 8
Sheik, R., Reji, S. A., Sharon, A., Avisha, M., & Nirmala, S. J. (2025) · Artificial Intelligence and Law · doi:10.1007/s10506-025-09459-5 · Cited by 5
Kaoutar, M. ’., Chaima, B. J., Bencharef, O., & Outmane, B. (2024) · International Conference on Intelligent Computing in Data Sciences (ICDS) · doi:10.1109/icds62089.2024.10756345 · Cited by 7
“Even with sophisticated models like GPT4 and Gemini, issues such as hallucinations [14] and nonsensical outputs remain prevalent.”
SeerahGPT: Retrieval Augmented Generation based Large Language Model
Obaid, S., & Bawany, N. Z. (2024) · International Conference on Open Source Systems and Technologies (ICOSST) · doi:10.1109/icosst64562.2024.10871159 · Cited by 6
“Similar approach is implemented for other domains such as law [12] [13], medicine [14], education [15], etc.”
Tapias, B. A. H., Guzmán, D. H., Zambam, N. J., Turatti, L., Rodríguez, F. A., Fröhlich, S., Staffen, M. R., Muñoz, P. M. C., Reyes, A. G., Soto, G., et al. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.164 · Cited by 12
Natural-language processing (NLP) and indexing, Part 1. Overview
Howes, D. (2025) · The Indexer · doi:10.3828/index.2025.26 · Cited by 4
Automated Theorem Provers Help Improve Large Language Model Reasoning
McGinness, L. P., & Baumgartner, P. (2024) · EPiC series in computing · doi:10.29007/2n9m · Cited by 12
“A recent famous example was a lawyer who submitted a legal brief generated by ChatGPT which contained many errors and false references [5, 6].”
BackgroundJeong, J., & Lee, S.-G. (2025) · IEEE Access · doi:10.1109/access.2025.3628960 · Cited by 4
“However, when deployed in domain-specific or high-stakes environments, LLMs face notable limitations, including in fields such as healthcare [2], [3], law [4], and finance [5].”
Legal Hallucinations and the Adoption of Artificial Intelligence in the Judiciary
Herrera-Tapias, B. A., & Guzmán, D. H. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.158 · Cited by 8
Comparison of explainability methods for hallucination analysis in LLMs
Papagiannopoulos, I., Koutalidis, H., Rempi, P., Ntanos, C., & Askounis, D. (2025) · Open Research Europe · doi:10.12688/openreseurope.20839.1 · Cited by 7
A Survey of Hallucination in Large Language Models
何, 金. (2026) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2026.151016 · Cited by 5
Law, Language, and Terminology. Challenges of Generative AI
Condello, A., Nunzio, G. M. D., & Vezzani, F. (2026) · International Journal for the Semiotics of Law - Revue internationale de Sémiotique juridique · doi:10.1007/s11196-026-10430-z · Cited by 3
Human-in-the-loop agent for product regulatory screening: Case study on concrete
Vergés, R., Gaspar, K., Forcada, N., & Hosseini, M. R. (2026) · Automation in Construction · doi:10.1016/j.autcon.2026.106876 · Cited by 4
Webb, J. S. (2026) · Minds and Machines · doi:10.1007/s11023-026-09771-2 · Cited by 7
“Yet, as Dahl et al., (2024 , pp.82–84) observe generic genAIs ‘system - atically overestimate’ their own reliability, and may uncritically accept prompters’ legal assumptions.”
InfluentialBenchmarking Legal RAG: The Promise and Limits of AI Statutory Surveys
Afane, M., Hariri, E., Ouyang, D., & Ho, D. E. (2026) · ACM Symposium on Computer Science and Law (CSLAW) · doi:10.1145/3788646.3789533 · Cited by 6
Self-citationYeleussinov, A., Buribayev, Z., Beisov, N., Kalzhanov, N. Y., Satymbekov, M., Akhatov, U. A., & Alimkulov, Y. (2026) · Applied Sciences · doi:10.3390/app16136777 · Cited by 4
LLM-Based Automated Hallucination Detection in Multilingual Customer Service RAG Applications
Patel, N. R., Mouratidis, H., & Zhi, K. N. K. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-96235-6_26 · Cited by 6
Xia, S.-J., Zhang, H., Jiang, Y., Chen, X., Chen, Y., Li, Z., Wan, Z., & Sun, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5731427 · Cited by 4
Dinakar, K., Lieberman, H. A., & Wu, M.-H. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716160 · Cited by 2
Ubiquity of LLM Hallucinations Across Critical Domains: A Survey
Singh, D., & Singh, A. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8197-6_9 · Cited by 8
Hybrid AI Enhancing European Drafting Legislation for a Better Regulation
Corazza, M., Longo, G., Zilli, L., Sante, E. D., Sapienza, S., & Palmirani, M. (2025) · International Conference on eDemocracy & eGovernment · doi:10.1109/icedeg65568.2025.11081650 · Cited by 3
Bridging the divide: technical research and application on legal judgment prediction
Zhang, C., & Meng, Y. (2025) · Artificial Intelligence and Law · doi:10.1007/s10506-025-09473-7 · Cited by 7
Enhancing Legal Document Understanding and Analysis Using Retriever-Augmented Generation (RAG)
Abdelsabour, M. A., & Gomaa, W. H. (2025) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa65733.2025.11167628 · Cited by 2
Where Does Legal AI Fail? Evaluating RAG Pipelines
Kim, Y., & Lee, W. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761151 · Cited by 5
“To understand failure mechanisms underlying incorrect responses, we categorize error sources using Dahl et al. (2024) and Magesh et al. (2024)’s hallucination taxonomy.”
Precedent Aware Legal Reasoning System for Turkish Jurisdiction with RAG Supported LLMs
Genç, U., Keskin, Ö. F., Akman, N. P., Berkol, A., & Birant, D. (2025) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit67332.2025.11267996 · Cited by 4
“As systematically examined by Dahl et al. [4], this problem is especially acute in the legal field, where trustworthy outputs are indispensable for both professional practice and public confidence.”
Evaluating AI for Law: Bridging the Gap with Open-Source Solutions
Bhambhoria, R. V., Dahan, S., Li, J., & Zhu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-12795-2_5 · Cited by 23
van Zijl, W., Greenslade, K., & Ecim, D. (2026) · Meditari Accountancy Research · doi:10.1108/medar-07-2025-3160 · Cited by 13
Chen, Y., Chen, M., Zhu, Y., Pei, J., Chen, S., Zhou, Y., (32470), Y. W., Zhou, Y., (31608), H. L., & Zhang, S. (2026) · Journal of Web Semantics · doi:10.1016/j.websem.2026.100879 · Cited by 16
Machines of justice: A systematic review of AI applications in policing and criminal justice
Farber, S. (2026) · The Police Journal Theory Practice and Principles · doi:10.1177/0032258x261439572 · Cited by 11
Hairurahman, H., Perdana, A., Wijaya, D. T., & Arifin, S. (2026) · Artificial Intelligence and Law · doi:10.1007/s10506-026-09507-8 · Cited by 3
Sharma, P. C., Khullar, S., Ahmad, I., & Nguyen, K. L. M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7320-1.ch012 · Cited by 2
AI and the Future of Public Courts
Vermeys, N., & Tan, J. (2026) · Cambridge University Press eBooks · doi:10.1017/9781009589086.030 · Cited by 2
Legal Prompt Engineering and How It Will Change the Way Lawyers Work
Müller-Peltzer, P., Tanczik, V., & Holz, A. (2025) · Law for professionals · doi:10.1007/978-3-031-78596-2_13 · Cited by 3
Lu, J., Li, F., Feng, L., Yu, Z., Lu, J., Qin, M., She, S., Jiang, H., Guo, Z., Xia, J., et al. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf534 · Cited by 2
“Compared to previous methods, the current approach achieves recognition of 46 types of microbial named entities and can identify various complex relationships between entities, as well as between entities and attributes. support [39, 40].”
Human-at-the-Helm: Redefining the role of artificial intelligence in student support
Rhodes, J. E. (2026) · Applied Developmental Science · doi:10.1080/10888691.2026.2683481 · Cited by 3
A Large Language Model based legal assistant for governance applicationsPreprint
Mamalis, M. E., Kalampokis, E., Fitsilis, F., Theodorakopoulos, G., & Tarabanis, K. A. (2024) · doi:10.31219/osf.io/94fmq · Cited by 2
Estimating and Correcting for Misclassification Error in Empirical Textual ResearchPreprint
Choi, J. H., & Connell, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4913179 · Cited by 4
Large Language Scholarship: Generative AI in the Legal AcademyPreprint
Rozenshtein, A. Z., & Frazier, K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5200768 · Cited by 2
LASG: Streamlining Legal Adjudication with AI-Enabled Summary Generation
Liu, Y., & Lin, Y.-F. (2024) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00360 · Cited by 1
“Additionally, Dahl et al. [14] investigate the extent of these hallucinations using an original suite of legal queries, comparing LLMs' responses to structured legal metadata and examining their consistency.”
Background
Metadata
- Authors
- Dahl, M., Magesh, V., Suzgun, M., & Ho, D. E.
- Affiliations
- Yale University (US)
- Stanford University (US)
- Corresponding author
- Dahl, Matthew
- Venue
- Journal of Legal Analysis
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-01-01
- Volume
- 16
- Issue
- 1
- Pages
- 64-93
- ISSN
- 1946-5319 (ISSN-L)
- 2161-7201
- OpenAlex
- W4400047099
- Cited by
- 559
- References
- 158
- Citations by year
- 2026: 355 · 2025: 148 · 2024: 55
- FWCI
- 677.59
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- The Journal of Legal Analysis (publishedVersion, cc-by-nc)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Social Sciences › Law › Artificial Intelligence in Law
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Law › Digitalization, Law, and Regulation
- Keywords
- large language models, ChatGPT, legal knowledge, legal reasoning, legal education, legal practice
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.