Correctness is not Faithfulness in Retrieval Augmented Generation Attributions
Abstract
Large language models (LLMs) have transformed information retrieval through chat interfaces, but their hallucination tendencies pose significant risks. While Retrieval Augmented Generation (RAG) with citations has emerged as a solution by allowing users to verify responses through source attribution, current evaluation approaches focus primarily on citation correctness - whether cited documents support the corresponding statements. This is insufficient and we introduce citation faithfulness - whether the model's reliance on cited documents is genuine rather than post-rationalized to fit pre-existing knowledge. Our contributions are threefold: (i) we introduce coherent notions of attribution and introduce the concept of citation faithfulness; (ii) we propose desiderata for citations beyond correctness and accuracy needed for trustworthy systems; and (iii) we emphasize evaluating citation faithfulness by studying post-rationalization. Through experimentation, we reveal prevalent post-rationalization issues, finding that up to 57% of citations lack faithfulness. This undermines reliable attribution and may result in misplaced trust, highlighting a critical gap in current LLM-based IR systems. We demonstrate why both citation correctness and faithfulness must be considered when deploying LLMs in IR applications, contributing to a broader discussion of building more reliable and transparent information access systems.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Source attribution is implicit and not causally grounded in the model's reasoning process.
“Source attribution is implicit and not causally grounded in the model's reasoning process.”
From From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents (2026) · cites this paper as Wallat et al., 2025
When inputs from multiple sources are combined within a shared context window, the model cannot reliably determine the origin of the content.
“V-M2: Source Attribution Failure in Multi-Source Contexts. When inputs from multiple sources are combined within a shared context window, the model cannot reliably determine the origin of the content (Wallat et al., 2025).”
From From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents (2026) · cites this paper as Wallat et al., 2025
Citation support does not establish causal reliance on evidence.
“Related work already identifies a divergence between answer quality and citation grounding under compression (Li et al., 2026a), while citation support does not establish causal reliance on evidence (Wallat et al., 2025).”
From The Attribution-Compression Frontier in Retrieval-Augmented Generation (2026) · cites this paper as Wallat et al., 2025
Wallat et al. (2025) distinguish citation correctness from causal faithfulness and investigate post-rationalization.
“Wallat et al. (2025) distinguish citation correctness from causal faithfulness and investigate post-rationalization.”
From The Attribution-Compression Frontier in Retrieval-Augmented Generation (2026) · cites this paper as Wallat et al., 2025
Cites
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 16,037 · see citing works
ChatGPT for good? On opportunities and challenges of large language models for education
Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., Günnemann, S., Hüllermeier, E., et al. (2023) · Learning and Individual Differences · doi:10.1016/j.lindif.2023.102274 · Cited by 7,326 · see citing works
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101 · see citing works
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069 · see citing works
Addressing Health-Related Misinformation on Social Media
Chou, W. S., Oh, A., & Klein, W. M. P. (2018) · JAMA · doi:10.1001/jama.2018.16865 · Cited by 938 · see citing works
Visualizing and Understanding Neural Models in NLP
Li, J., Chen, X., Hovy, E. H., & Jurafsky, D. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1082 · Cited by 673 · see citing works
RAGAs: Automated Evaluation of Retrieval Augmented Generation
Es, S., James, J., Espinosa Anke, L., & Schockaert, S. (2024) · Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/2024.eacl-demo.16 · Cited by 651 · see citing works
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Jacovi, A., Marasović, A., Miller, T., & Goldberg, Y. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445923 · Cited by 545 · see citing works
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?
Jacovi, A., & Goldberg, Y. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.386 · Cited by 503 · see citing works
Regulating ChatGPT and other Large Generative AI Models
Hacker, P., Engel, A., & Mauer, M. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594067 · Cited by 466 · see citing works
e-SNLI: Natural language inference with natural language explanations
Camburu, O.-M., Rocktäschel, T., Lukasiewicz, T., & Blunsom, P. (2018) · arXiv · doi:10.48550/arxiv.1812.01193 · Cited by 367 · see citing works
Large language models in health care: Development, applications, and challenges
Yang, R., Tan, T. F., Lu, W., Thirunavukarasu, A. J., Ting, D. S. W., & Liu, N. (2023) · Health Care Science · doi:10.1002/hcs2.61 · Cited by 366 · see citing works
KILT: a Benchmark for Knowledge Intensive Language Tasks
Petroni, F., Piktus, A., Fan, A., Lewis, P., Yazdani, M., De Cao, N., Thorne, J., Jernite, Y., Karpukhin, V., Maillard, J., et al. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.200 · Cited by 357 · see citing works
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., & Zaharia, M. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.272 · Cited by 353 · see citing works
Transformer Feed-Forward Layers Are Key-Value Memories
Geva, M., Schuster, R., Berant, J., & Levy, O. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.446 · Cited by 353 · see citing works
AI-Generated Medical Advice—GPT and Beyond
Haupt, C. E., & Marks, M. (2023) · JAMA · doi:10.1001/jama.2023.5321 · Cited by 346 · see citing works
Sadiku, M. N. O., Kotteti, C. M. M., & Sadiku, J. O. (2024) · International Journal of Advances in Scientific Research and Engineering · doi:10.31695/ijasre.2024.1.1 · Cited by 313 · see citing works
Risks and Benefits of Large Language Models for the Environment
Rillig, M. C., Ågerstrand, M., Bi, M., Gould, K. A., & Sauerland, U. (2023) · Environmental Science & Technology · doi:10.1021/acs.est.3c01106 · Cited by 272 · see citing works
Misinformation as a Misunderstood Challenge to Public Health
Southwell, B. G., Niederdeppe, J., Cappella, J. N., Gaysynsky, A., Kelley, D., Oh, A., Peterson, E. B., & Chou, W. S. (2019) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2019.03.009 · Cited by 245 · see citing works
The power of noise: Redefining retrieval for rag systems
Cuconasu, F., Trappolini, G., Siciliano, F., Filice, S., Campagnano, C., Maarek, Y., Tonellotto, N., & Silvestri, F. (2024) · Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3626772.3657834 · Cited by 236 · see citing works
Nan, X., Wang, Y., & Thier, K. (2022) · Social Science & Medicine · doi:10.1016/j.socscimed.2022.115398 · Cited by 221 · see citing works
Enabling Large Language Models to Generate Text with Citations
Gao, T., Yen, H., Yu, J., & Chen, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.398 · Cited by 216 · see citing works
Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT
Wu, Z., Chen, Y., Kao, B., & Liu, Q. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.383 · Cited by 159 · see citing works
ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
Saad-Falcon, J., Khattab, O., Potts, C., & Zaharia, M. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.20 · Cited by 148 · see citing works
Evaluating Verifiability in Generative Search Engines
Liu, N., Zhang, T., & Liang, P. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.467 · Cited by 143 · see citing works
Evaluating Verifiability in Generative Search Engines
Liu, N. F., Zhang, T., & Liang, P. (2023) · arXiv · Cited by 143 · see citing works
Legal Knowledge and Information Systems
(2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia395 · Cited by 120 · see citing works
Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AIPreprint
Ahmad, M. Z., Yaramic, I., & Roy, T. D. (2023) · Preprints.org · doi:10.20944/preprints202310.1662.v1 · Cited by 102 · see citing works
Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI
Ahmad, M. A., Yaramis, I., & Roy, T. D. (2023) · arXiv · doi:10.48550/arxiv.2311.01463 · Cited by 84 · see citing works
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Adlakha, V., BehnamGhader, P., Lu, X. H., Meade, N., & Reddy, S. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00667 · Cited by 74 · see citing works
Measuring Attribution in Natural Language Generation Models
Rashkin, H., Nikolaev, V., Lamm, M., Aroyo, L., Collins, M., Das, D., Petrov, S., Tomar, G. S., Turc, I., & Reitter, D. (2023) · Computational Linguistics · doi:10.1162/coli_a_00486 · Cited by 71 · see citing works
Understanding trust formation in digital information sources: The case of Wikipedia
Rowley, J., & Johnson, F. (2013) · Journal of Information Science · doi:10.1177/0165551513477820 · Cited by 64 · see citing works
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering
Neeman, E., Aharoni, R., Honovich, O., Choshen, L., Szpektor, I., & Abend, O. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.559 · Cited by 41 · see citing works
Model agnostic interpretability of rankers via intent modelling
Singh, J., & Anand, A. (2020) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3351095.3375234 · Cited by 38 · see citing works
Self-citationBastings, J., Ebert, S., Zablotskaia, P., Sandholm, A., & Filippova, K. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.64 · Cited by 37 · see citing works
“According to . . . ”: Prompting Language Models Improves Quoting from Pre-Training Data
Weller, O., Marone, M., Weir, N., Lawrie, D., Khashabi, D., & Durme, B. V. (2024) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2024.eacl-long.140 · Cited by 34 · see citing works
Measuring Attribution in Natural Language Generation Models
Rashkin, H., Nikolaev, V., Lamm, M., Aroyo, L., Collins, M., Das, D., Petrov, S., Tomar, G. S., Turc, I., & Reitter, D. (2021) · arXiv · doi:10.48550/arxiv.2112.12870 · Cited by 34 · see citing works
On the Evaluation of Machine-Generated Reports
Mayfield, J., Yang, E., Lawrie, D., MacAvaney, S., McNamee, P., Oard, D. W., Soldaini, L., Soboroff, I. M., Weller, O., Kayi, E. S., et al. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657846 · Cited by 26 · see citing works
Attribute First, then Generate: Locally-attributable Grounded Text Generation
Slobodkin, A., Hirsch, E., Cattan, A., Schuster, T., & Dagan, I. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.182 · Cited by 17 · see citing works
Towards Benchmarking the Utility of Explanations for Model Debugging
Idahl, M., Lyu, L., Gadiraju, U., & Anand, A. (2021) · Workshop on Trustworthy Natural Language Processing (TrustNLP) · doi:10.18653/v1/2021.trustnlp-1.8 · Cited by 14 · see citing works
Self-citationChen, C., Merullo, J., & Eickhoff, C. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657841 · Cited by 13 · see citing works
Sadeghi, M., Pöttgen, D., Ebel, P., & Vogelsang, A. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3627043.3659573 · Cited by 13 · see citing works
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 11 · see citing works
Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
Ye, X., Sun, R., Arık, S. Ö., & Pfister, T. (2024) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2024.naacl-long.346 · Cited by 10 · see citing works
Zhang, W., Aliannejadi, M., Yuan, Y., Pei, J., Huang, J.-H., & Kanoulas, E. (2024) · International Conference on Natural Language Generation · doi:10.18653/v1/2024.inlg-main.35 · Cited by 7 · see citing works
An Evaluation Framework for Attributed Information Retrieval using Large Language Models
Djeddal, H., Erbacher, P., Toukal, R., Soulier, L., Pinel-Sauvagnat, K., Katrenko, S., & Tamine, L. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679172 · Cited by 5 · see citing works
Causal Probing for Dual Encoders
Wallat, J., Hinrichs, H., & Anand, A. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679556 · Cited by 3 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking
Fang, H., Tao, S., Chen, N., Chang, K.-X., & Sakai, T. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769493 · Cited by 6 · see citing works
Zhao, Y., Miao, Y., Guo, R., Luo, Y., Wang, H., & Wu, Y. X. (2026) · Journal of Medical Internet Research · doi:10.2196/90046 · Cited by 2 · see citing works
“Recent scholar-ship supports this distinction, showing that citation presence or citation plausibility is not equivalent to citation and source correctness, because apparently correct citations may still reflect post hoc rationalization rather than genuine evidence use [186].”
van Dort, I., & Heuss, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_35 · Cited by 1 · see citing works
Self-citationFACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG
Dassen, M., Kotula, R., Murray, K., Yates, A., Lawrie, D., Kayi, E. S., Mayfield, J., & Duh, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21289-4_18 · Cited by 3 · see citing works
Mosa, M. A. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12188-8 · Cited by 1 · see citing works
“Recent analyses also emphasize that citation correctness can still be unfaithful due to post-hoc attributions, motivating explicit faithfulness gates and evidence-usage checks in high-stakes settings ([56]; Wällat & de Rijke, 2025; [57]).”
Mala, C. S., Gezi̇ci, G., & Giannotti, F. (2026) · Machine Learning · doi:10.1007/s10994-026-07121-y · Cited by 1 · see citing works
HALT-RAG: Hallucination-Tolerant Retrieval-Augmented QA for Scientific Literature
Saha, P., Bhattacharjee, S., & Nath, A. R. (2026) · International Conference on Power, Electronics, Communications, Computing, and Intelligent Infrastructure (PECCII) · doi:10.1109/peccii70991.2026.11661908 · Cited by 1 · see citing works
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
Dash, P., Ge, T., Jain, A., Shah, T., & Shang, Z. (2026) · arXiv · doi:10.48550/arxiv.2606.04329
“When inputs from multiple sources are combined within a shared context window, the model cannot reliably determine the origin of the content (Wallat et al., 2025).”
Workshop on Conversational Search for Complex Information Needs
Petcu, R., Yazan, M., Hoveyda, M., Qi, J., & de Rijke, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_19
Self-citationKasneci, G., & Kasneci, E. (2026) · AI and Ethics · doi:10.1007/s43681-026-01132-0 · Cited by 1 · see citing works
“Systems may present claims as well-supported even when evidence is weak, outdated, selectively used, or incorrectly synthesized (Wallat et al., 2025).”
A Hybrid LLM-Based Architecture for Reliable Standardization of Heterogeneous Grant Information
Strykowski, S., Leszczyński, C., Kumor, S., & Śliwicki, M. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-26363-6_19
Designing a Local RAG-Based Intelligent Tutoring System for Domain-Specific Education
Gala, A. D. C. O. S., Marcondes, F. S., Machado, J. M., & Nováis, P. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2891-1_13 · Cited by 1 · see citing works
Deletion Isn't Enough: Auditing RAG for Selective Forgetting
Tavakoli, L., & Sanderson, M. (2026) · Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3805712.3808545
Wu, J., Li, J., Ning, Z., & Wang, L. (2026) · Machine Learning · doi:10.1007/s10994-026-07109-8
“…but not equivalent: a generated answer may be factually correct without being supported by the provided evidence, while an answer that appears well aligned with the retrieved passages may still be incomplete or incorrect with respect to the gold answer (Li et al., 2024; Wallat et al., 2025).”
AMOS: Active Mining with Observable Steps for Agenda-Driven Review Knowledge Discovery
Yeh, C.-Y., Huang, W., Chen, H.-W., Wang, C., Yang, D.-N., Lee, W.-C., Yu, P. S., & Chen⋆, M.-S. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817839
Baek, C. (2026) · Sensors · doi:10.3390/s26165246
“What we find (SQ4, the faithfulness question defined with the other four in Section 4) aligns with both audits above [32,36] and raises the same concern regarding streaming industrial triage.”
FaithRAG: Retrieval-Augmented Generation for Faithful Video Understanding
Tsai, P., & Gao, Y. (2026) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-026-2947-4
Traceability and Source Authority Guardrails for Agentic RAG-Based Financial Claim Verification
Thamrin, D. S., Lubis, M., Fansyah, E. A., Fauzan, R. A., & Asyam, M. R. D. (2026) · International Conference on Electronics Representation and Algorithm (ICERA) · doi:10.1109/icera72709.2026.11666732
“Wallat et al. argue that correctness and faithfulness in retrieval-augmented attribution are not equivalent, meaning that an answer may be correct while its attribution remains unreliable [23].”
Ghaywat, V., Singh, A., Shahade, A. K., Khan, W., & Deshmukh, P. V. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02373-y
Hirahata, Y., & Sakahira, F. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02075-5
“It has been pointed out that, even with RAG, claims that are not supported by—or that contra-dict—the retrieved evidence can be generated [21, 26].”
Beyond Output Faithfulness: Claim-Centered Relational Auditability for Source-Grounded Generative AI
Wang, J., & Liu, P. (2026) · Information · doi:10.3390/info17100992
A Voice-Based Retrieval Augmented Generation System for Document-Restricted Question Answering
Sreedhar, A., Rajakumar, K., Rohan Kumar, B., V, Kasetty, S. B., & Margret, I. N. (2026) · International Conference on Intelligent Computing and Sustainable Innovations in Technology (IC-SIT) · doi:10.1109/ic-sit69723.2026.11735988
“As shown by J. Wallat et al., correctness is not necessarily a guarantee of faithfulness in RAG-based attributions, showing that the produced answers can be correct yet not faithful to the evidence [17], [18].”
- Authors
- Wallat, J., Heuss, M., Rijke, M. D., & Anand, A.
- Affiliations
- L3S Research Center (DE)
- University of Amsterdam (NL)
- Delft University of Technology (NL)
- Venue
- Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)
- Publisher
- ACM
- Published
- 2025-07-18
- Pages
- 22-32
- OpenAlex
- W4412673546
- Cited by
- 21
- References
- 47
- Citations by year
- 2026: 20 · 2025: 1
- FWCI
- 25.20
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) (publishedVersion)
- Funders
- German Research Foundation (DFG) (AN 996/1-1)
- European Union's Horizon Europe (101070212)
- Lower Saxony Ministry of Science and Culture (MWK) (HybrInt)
- Dutch Research Council (024.004.022,NWA.1389.20.\-183,KICH3.LTP.20.006)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- retrieval-augmented generation, source attribution, hallucinations, large language models, information retrieval, evaluation metrics, trustworthy systems
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.
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
