The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Revisiting Relation Extraction in the era of Large Language Models
Open accessAbstract
Relation extraction (RE) is the core NLP task of inferring semantic relationships between entities from text.Standard supervised RE techniques entail training modules to tag tokens comprising entity spans and then predict the relationship between them.Recent work has instead treated the problem as a sequence-tosequence task, linearizing relations between entities as target strings to be generated conditioned on the input.Here we push the limits of this approach, using larger language models (GPT-3 and Flan-T5 large) than considered in prior work and evaluating their performance on standard RE tasks under varying levels of supervision.We address issues inherent to evaluating generative approaches to RE by doing human evaluations, in lieu of relying on exact matching.Under this refined evaluation, we find that: (1) Few-shot prompting with GPT-3 achieves near SOTA performance, i.e., roughly equivalent to existing fully supervised models; (2) Flan-T5 is not as capable in the fewshot setting, but supervising and fine-tuning it with Chain-of-Thought (CoT) style explanations (generated via GPT-3) yields SOTA results.We release this model as a new baseline for RE tasks 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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This dependency is a shared limitation of agentic memory systems that rely on LLM-based structural inference, as they are susceptible to extraction errors and hallucinations (Pan et al., 2024; Xi et al., 2025; Wadhwa et al., 2023).”
From MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents (2026) · cites this paper as Wadhwa et al., 2023
Experimental — accuracy not yet measured
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
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
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
Lafferty, J., McCallum, A., & Pereira, F. C. N. (2001) · ScholarlyCommons (University of Pennsylvania) · Cited by 12,935
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263
Support vector machine learning for interdependent and structured output spaces
Tsochantaridis, I., Hofmann, T., Joachims, T., & Altun, Y. (2004) · International Conference on Machine Learning · doi:10.1145/1015330.1015341 · Cited by 1,493
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441
Modeling Relations and Their Mentions without Labeled Text
Riedel, S., Yao, L., & McCallum, A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15939-8_10 · Cited by 1,333
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101
Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
Lu, Y., Bartolo, M., Moore, A., Riedel, S., & Stenetorp, P. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.556 · Cited by 610
Research works printed but not linked: 2
- Brown Tom, Mann Benjamin, Ryder Nick, Subbiah Melanie, Jared D Kaplan Prafulla Dhariwal, Neelakantan Arvind, Shyam Pranav, Sastry Girish, Askell Amanda, Agarwal Sandhini, Herbert-Voss Ariel, Krueger Gretchen, Henighan Tom, Child Rewon, Ramesh Aditya, Ziegler Daniel, Wu Jeffrey, Winter Clemens, Hesse Chris, Chen Mark, Sigler Eric, Litwin Mateusz, Gray Scott, Chess Benjamin, Clark Jack, Berner Christopher, Sam McCandlish Alec Radford, Sutskever Ilya, and Amodei Dario. 2020a. Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33, pages 1877– 1901. Curran Associates, Inc.
- Paolini Giovanni, Athiwaratkun Ben, Krone Jason, Ma Jie, Achille Alessandro, ANUBHAI RISHITA, Santos Cicero Nogueira dos, Xiang Bing, and Soatto Stefano. 2021. Structured prediction as translation between augmented natural languages. In International Conference on Learning Representations.
Cited by
Sorted by citations
A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4
Kalyan, K. S. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100048 · Cited by 335
Miao, J., Thongprayoon, C., Suppadungsuk, S., Valencia, O. A. G., & Cheungpasitporn, W. (2024) · Medicina · doi:10.3390/medicina60030445 · Cited by 198
Hadi, M. U., Al-Tashi, Q., Qureshi, R., Shah, A., Muneer, A., Irfan, M., Zafar, A., Shaikh, M. B., Akhtar, N., Hassan, S. Z., et al. (2023) · doi:10.36227/techrxiv.23589741.v4 · Cited by 193
Dennstädt, F., Zink, J., Putora, P. M., Hastings, J., & Čihorić, N. (2024) · Systematic Reviews · doi:10.1186/s13643-024-02575-4 · Cited by 191
Metadata
- Authors
- Wadhwa, S., Amir, S., & Wallace, B.
- Affiliations
- Northeastern University (US)
- ORCID
- Wallace, Byron
- Venue
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2023
- Volume
- 2023
- Pages
- 15566-15589
- ISSN
- 0736-587X (ISSN-L)
- PMC
- PMC10482322
- OpenAlex
- W4385571451
- Cited by
- 207
- References
- 32
- Citations by year
- 2026: 53 · 2025: 74 · 2024: 65 · 2023: 14
- FWCI
- 36.50
- 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)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- National Science Foundation (1750978)
- National Institutes of Health (5r01lm012086-08)
- U.S. National Library of Medicine (R01-LM012086)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- relation extraction, large language models, GPT-3, Flan-T5, few-shot prompting, chain-of-thought prompting, human evaluation, sequence-to-sequence generation, entity relationships, fine-tuning
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
