The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
DRAGIN: Dynamic Retrieval Augmented Generation based on the Real-time Information Needs of Large Language Models
Open accessAbstract
Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs).There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve).However, current dynamic RAG methods fall short in both aspects.Firstly, the strategies for deciding when to retrieve often rely on static rules.Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM's most recent sentence or the last few tokens, while the LLM's information needs may span across the entire context.To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the Information Needs of LLMs.Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's information needs during the text generation process.We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets.Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method 1 .
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 cited source says what the claim attributes to it.
In the citing paper
“Su et al. [111] directly formulate queries based on the internal attention distribution of LLMs (Figure 2) and improve the performance of RAG for nearly 20% on several benchmark datasets without changing the retrieval system.”
From Foundations of GenIR (2025) · cites this paper as [111]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 41
- Sebastian Borgeaud, Arthur Mensch, Jordan Hoff- mann, Trevor Cai, Eliza Rutherford, Katie Milli- can, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from tril- lions of tokens. In International conference on ma- chine learning, pages 2206-2240. PMLR.
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901.
- Jia Chen, Haitao Li, Weihang Su, Qingyao Ai, and Yiqun Liu. 2023. Thuir at wsdm cup 2023 task 1: Unbiased learning to rank. arXiv preprint arXiv:2304.12650. · arXiv
- Xuesong Chen, Ziyi Ye, Xiaohui Xie, Yiqun Liu, Xi- aorong Gao, Weihang Su, Shuqi Zhu, Yike Sun, Min Zhang, and Shaoping Ma. 2022. Web search via an efficient and effective brain-machine interface. In Proceedings of the Fifteenth ACM International Con- ference on Web Search and Data Mining, pages 1569- 1572.
- Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311. · arXiv
- Yan Fang, Jingtao Zhan, Qingyao Ai, Jiaxin Mao, Weihang Su, Jia Chen, and Yiqun Liu. 2024. Scaling laws for dense retrieval. arXiv preprint arXiv:2403.18684. · arXiv
- James Ferguson, Matt Gardner, Hannaneh Hajishirzi, Tushar Khot, and Pradeep Dasigi. 2020. Iirc: A dataset of incomplete information reading compre- hension questions. arXiv preprint arXiv:2011.07127. · arXiv
- Luyu Gao and Jamie Callan. 2021. Condenser: a pre-training architecture for dense retrieval. arXiv preprint arXiv:2104.08253. · arXiv
- Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, and Jonathan Berant. 2021. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346- 361.
- Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasu- pat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International confer- ence on machine learning, pages 3929-3938. PMLR.
- Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps. arXiv preprint arXiv:2011.01060. · arXiv
- Gautier Izacard and Edouard Grave. 2020. Leverag- ing passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282. · arXiv
- Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of halluci- nation in natural language generation. ACM Comput- ing Surveys, 55(12):1-38.
- Zhengbao Jiang, Luyu Gao, Jun Araki, Haibo Ding, Zhiruo Wang, Jamie Callan, and Graham Neubig. 2022. Retrieval as attention: End-to-end learning of retrieval and reading within a single transformer. arXiv preprint arXiv:2212.02027. · arXiv
- Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Ac- tive retrieval augmented generation. arXiv preprint arXiv:2305.06983. · arXiv
- Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172. · arXiv
- Haitao Li, Jia Chen, Weihang Su, Qingyao Ai, and Yiqun Liu. 2023a. Towards better web search perfor- mance: Pre-training, fine-tuning and learning to rank. arXiv preprint arXiv:2303.04710. · arXiv
- Haitao Li, Weihang Su, Changyue Wang, Yueyue Wu, Qingyao Ai, and Yiqun Liu. 2023b. Thuir@ col- iee 2023: Incorporating structural knowledge into pre-trained language models for legal case retrieval. arXiv preprint arXiv:2305.06812. · arXiv
- Haitao Li, Changyue Wang, Weihang Su, Yueyue Wu, Qingyao Ai, and Yiqun Liu. 2023c. Thuir@ coliee 2023: More parameters and legal knowledge for legal case entailment. arXiv preprint arXiv:2305.06817. · arXiv
- Junyi Li, Tianyi Tang, Wayne Xin Zhao, Jingyuan Wang, Jian-Yun Nie, and Ji-Rong Wen. 2023d. The web can be your oyster for improving large language models. arXiv preprint arXiv:2305.10998. · arXiv
- Tianyu Liu, Yizhe Zhang, Chris Brockett, Yi Mao, Zhifang Sui, Weizhu Chen, and Bill Dolan. 2021. A token-level reference-free hallucination detection benchmark for free-form text generation. arXiv preprint arXiv:2104.08704. · arXiv
- Yixiao Ma, Yueyue Wu, Weihang Su, Qingyao Ai, and Yiqun Liu. 2023. Caseencoder: A knowledge- enhanced pre-trained model for legal case encoding. arXiv preprint arXiv:2305.05393. · arXiv
- Joshua Maynez, Shashi Narayan, Bernd Bohnet, and Ryan McDonald. 2020. On faithfulness and factu- ality in abstractive summarization. arXiv preprint arXiv:2005.00661. · arXiv
- Niklas Muennighoff. 2022. Sgpt: Gpt sentence embeddings for semantic search. arXiv preprint arXiv:2202.08904. · arXiv
- Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. In-context retrieval-augmented lan- guage models. arXiv preprint arXiv:2302.00083. · arXiv
- Stephen Robertson, Hugo Zaragoza, et al. 2009. The probabilistic relevance framework: Bm25 and be- yond. Foundations and Trends® in Information Re- trieval, 3(4):333-389.
- Teven Le Scao, Angela Fan, Christopher Akiki, El- lie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, et al. 2022. Bloom: A 176b- parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100. · arXiv
- Hemlata Shelar, Gagandeep Kaur, Neha Heda, and Poorva Agrawal. 2020. Named entity recognition ap- proaches and their comparison for custom ner model. Science & Technology Libraries, 39(3):324-337.
- Weijia Shi, Sewon Min, Michihiro Yasunaga, Min- joon Seo, Rich James, Mike Lewis, Luke Zettle- moyer, and Wen-tau Yih. 2023. Replug: Retrieval- augmented black-box language models. arXiv preprint arXiv:2301.12652. · arXiv
- Weihang Su, Qingyao Ai, Xiangsheng Li, Jia Chen, Yiqun Liu, Xiaolong Wu, and Shengluan Hou. 2023a. Wikiformer: Pre-training with structured information of wikipedia for ad-hoc retrieval. arXiv preprint arXiv:2312.10661. · arXiv
- Weihang Su, Qingyao Ai, Yueyue Wu, Yixiao Ma, Haitao Li, and Yiqun Liu. 2023b. Caseformer: Pre-training for legal case retrieval. arXiv preprint arXiv:2311.00333. · arXiv
- Weihang Su, Xiangsheng Li, Yiqun Liu, Min Zhang, and Shaoping Ma. 2023c. Thuir2 at ntcir-16 session search (ss) task. arXiv preprint arXiv:2307.00250. · arXiv
- Weihang Su, Changyue Wang, Qingyao Ai, Yiran Hu, Zhijing Wu, Yujia Zhou, and Yiqun Liu. 2024. Unsu- pervised real-time hallucination detection based on the internal states of large language models. arXiv preprint arXiv:2403.06448. · arXiv
- Hugo Touvron, Louis Martin, Kevin Stone, Peter Al- bert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023b. Llama 2: Open founda- tion and fine-tuned chat models. arXiv preprint arXiv:2307.09288. · arXiv
- Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171. · arXiv
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits rea- soning in large language models. Advances in Neural Information Processing Systems, 35:24824-24837.
- Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Ben- gio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answer- ing. arXiv preprint arXiv:1809.09600. · arXiv
- Ziyi Ye, Xiaohui Xie, Qingyao Ai, Yiqun Liu, Zhihong Wang, Weihang Su, and Min Zhang. 2024. Relevance feedback with brain signals. ACM Transactions on Information Systems, 42(4):1-37.
- ChengXiang Zhai. 2008. Statistical language models for information retrieval. Synthesis lectures on human language technologies, 1(1):1-141.
- Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher De- wan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068. · arXiv
- Chunting Zhou, Graham Neubig, Jiatao Gu, Mona Diab, Paco Guzman, Luke Zettlemoyer, and Marjan Ghazvininejad. 2020. Detecting hallucinated con- tent in conditional neural sequence generation. arXiv preprint arXiv:2011.02593. Prompt 4: exemplars of HotpotQA RAG Question: Jeremy Theobald and Christopher Nolan share what profession? Answer: Jeremy Theobald is an actor and producer. Christopher Nolan is a director, producer, and screenwriter. Therefore, they both share the profession of being a producer. So the answer is producer. Question: What film directed by Brian Patrick Butler was inspired by a film directed by F.W. Murnau? Answer: Brian Patrick Butler directed the film The Phantom Hour. The Phantom Hour was inspired by the films such as Nosferatu and The Cabinet of Dr. Caligari. Of these Nosferatu was directed by F.W. Murnau. So the answer is The Phantom Hour. Question: How many episodes were in the South Korean television series in which Ryu Hye-young played Bo-ra? Answer: The South Korean television series in which Ryu Hye-young played Bo-ra is Reply 1988. The number of episodes Reply 1988 has is 20. So the answer is 20. Question: Were Lonny and Allure both founded in the 1990s? Answer: Lonny (magazine) was founded in 2009. Allure (magazine) was founded in 1991. Thus, of the two, only Allure was founded in 1990s. So the answer is no. Question: Vertical Limit stars which actor who also played astronaut Alan Shepard in "The Right Stuff"? Answer: The actor who played astronaut Alan Shepard in "The Right Stuff" is Scott Glenn. The movie Vertical Limit also starred Scott Glenn. So the answer is Scott Glenn. Question: What was the 2014 population of the city where Lake Wales Medical Center is located? Answer: Lake Wales Medical Center is located in the city of Polk County, Florida. The population of Polk County in 2014 was 15,140. So the answer is 15,140. Question: Who was born first? Jan de Bont or Raoul Walsh? Answer: Jan de Bont was born on 22 October 1943. Raoul Walsh was born on March 11, 1887. Thus, Raoul Walsh was born the first. So the answer is Raoul Walsh. Question: In what country was Lost Gravity manufactured? Answer: The Lost Gravity (roller coaster) was manufactured by Mack Rides. Mack Rides is a German company. So the answer is Germany. Context: · arXiv
Cited by
Sorted by citations
Items 101–136 of 136
KGtelescope: Knowledge Graph Guided Model Routing for Factual Question AnsweringPreprint
Spahiu, B., Maccarini, M., Rula, A., & Palmonari, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7067175
TraceRAG: Trajectory-Aware Concept Tracing for Faithful Retrieval-Augmented Generation
Zheng, J., Ruan, M., & Yang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3432-5_7
Towards Adaptive and Retriever-friendly Retrieval-augmented Generation via Reinforcement Learning
FANG, Y., Yu, H.-T., Joho, H., & Fujita, S. (2026) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3805713.3820432
Adaptive Token-Aware Query Reformulation for Text-to-Image Retrieval
Kim, S. A., Kim, M., Lee, Y., Kim, J., Han, J., & Park, E. K. (2026) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3805713.3820400
Incentivizing Retrieval-Augmented Generation via Inner Adaptive Context Selection
Cui, C., Shen, L., Fan, H., Zhu, S., Dai, F., & Li, B. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809671
Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders
Lee, J., Jang, S., Kang, S., & Yu, H. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809656
Query-Aware Context Selection for Retrieval-Augmented Generation
Iratni, M., Boughanem, M., & Dkaki, T. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809959
Su, W., Chen, X., Wu, Y., Ai, Q., & Liu, Y. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809928 · Cited by 5
Self-citationLatent Retrieval Augmented Generation
Zhou, S., Chen, J., Ling, R., Fan, T., & Wang, H. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809870
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Dai, L., Sun, L., Cao, F., Rao, Z., Yang, C., Liu, H., & Xiong, H. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808544 · Cited by 2
Chen, P., Bie, H., Qiu, S., & Cao, Y. (2026) · International Conference on Algorithms, Software Engineering and Network Security (ASENS) · doi:10.1109/asens69964.2026.11605379
Gondane, M. S. (2026) · doi:10.31979/etd.22wa-zpjc
Budgeted Multi-Hop Retrieval Agents with Evidence-Chain Reliability and Cost-Aware Abstention
Kong, C. (2026) · Journal of Knowledge Learning and Science Technology · doi:10.60087/jklst.vol5.n2.006
Kuo, C.-E., Wu, C., Trappey, A. J. C., & Hung, L. P. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7243293
SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems
Raza, M. O., Yang, S. L., & Srinivasan, S. (2026) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit70676.2026.11631166 · Cited by 1
The Evolution of SEO in the Era of Generative AI: A Business Intelligence Perspective
Roumeliotis, K. I., Margaris, D., Spiliotopoulos, D., & Vassilakis, C. (2026) · Electronics · doi:10.3390/electronics15163541
DM-RAG: Enhancing User Support in Dameng Databases with Retrieval-Augmented Generation
Huang, Q., Liu, K., Deng, L., Zhang, S., Hu, C., Qian, T., Yan, X., & Jiang, J. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00304
Regime-Aware Selective Knowledge Consolidation in Language-Model SystemsPreprint
Andreani, A. C., & Boaretto, B. R. R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7327626
Efficient Adaptive Retrieval-Augmented Generation via Temporal Question Classification
Pletenev, S., Salnikov, M., Panchenko, A., & Konovalov, V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37685-5_50
Adversarial Fact Editing and Active RAG Defenses for Robust Large Language Model Bash Execution
Adler, E., Seitz, C., Holz, L., Loevenich, J. F., & Lopes, R. R. F. (2026) · Conference on Local Computer Networks · doi:10.1109/lcn67947.2026.11660783
Jeong, S., & Suh, Y. (2026) · Electronics · doi:10.3390/electronics15184231
Xu, Z., Dai, X., Wang, B., & Tian, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38059-3_29
Liu, Y., Yang, B., & Zhang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5693-8_13
Self-citationKhedkar, R. A., & Pant, S. P. (2026) · Journal of Intelligent & Fuzzy Systems · doi:10.1177/18758967261492002
Noise-Gated Retrieval: Embedding-Based Context Compression for Cost-Aware RAG
Lavado, A. M., Alcoforado, A., & Costa, A. H. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39892-5_30
Chen, S., Yi, X., Guo, C., Huang, Y., Li, T., & Zheng, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37682-4_22
Li, Z., Gao, C., Wang, Z., Wang, X., Lu, Y., & You, D. (2026) · Expert Systems · doi:10.1111/exsy.70455
AMRAG: Adaptive Multi-step Retrieval-Augmented Generation for Complex Question Answering
Zhang, N., Wang, X., Luo, X., & Gao, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728424
DMG-RAG: Dynamic Multi-Grained Retrieval Augmented Generation for Multi-Hop QA
Pei, Y., Maimaiti, M., Chen, Y., Le, W., Xie, Z., & Chen, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729924
Epistemic State Modeling for Adaptive Retrieval-Augmented Generation
Liang, N., Yang, C., Yang, K., Gao, J., Wu, Q., & Wang, M. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728644
AdaCache: Efficient and Robust Noise-Resistant Semantic Caching for RAG
Chen, S., Zhang, L., & Lee, S.-W. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728681
Cost-Aware Gated Retrieval: Decoupling Retrieval Initiation from Evidence-Conditioned EscalationPreprint
Hao, Z., & Li, Y. (2026) · Research Square · doi:10.21203/rs.3.rs-11499644/v1
Benchmark-Defined Adaptive Candidate Reranking for Indonesian Multi-Hop Question Answering
Rahman, I. A., & Wibowo, A. (2026) · Journal of Computing Theories and Applications · doi:10.62411/jcta.18163
DataDescribe: Auto-Generated Source Descriptors for LLM-Agent Retrieval over Heterogeneous Data
Agrawal, R., Mazanec, G., Kanani, P., Gujarathi, A., & Sudan, M. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840921
State-Conditioned Evidence Coalition Selection for Multi-Hop Retrieval-Augmented Question Answering
Jin, X., Du, Y., Li, M., & Wang, B. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840801
Few-Shot Named Entity Recognition with Contrastive Knowledge Prompting and Dynamic Retrieval
Huo, H., & Wu, M. (2026) · IEEE International Conference on Computer and Communication Engineering Technology (CCET) · doi:10.1109/ccet71000.2026.11747977
Metadata
- Authors
- Su, W., Tang, Y., Ai, Q., Wu, Z., & Liu, Y.
- Affiliations
- Tsinghua University (CN)
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 12991-13013
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4402671152
- Cited by
- 81
- References
- 0
- Citations by year
- 2026: 47 · 2025: 27 · 2024: 7
- FWCI
- 23.90
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- large language models, information needs, query generation, text generation
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
