Elamur Research⌕
☰
home / papers / 2024 / Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models

Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models

Paper · 2024 · Miaoran Li, Baolin Peng, Michel Galley et al.

Summary

LLM outputs often contain hallucinated facts. Most automated fact-checking systems depend on costly fine-tuning, and existing benchmarks mostly test short claims taken from Wikipedia rather than long, information-dense LLM answers. The authors propose SELF-CHECKER, a training-free framework built from prompted LLM modules that work in a few-shot setting:

  • a claim processor that splits text into atomic claims,
  • a query generator for retrieval (Bing search in their setup),
  • an evidence seeker that selects supporting sentences,
  • a verdict counselor that assigns graded veracity labels.

A policy agent decides step by step which module to call next. The authors also release BINGCHECK, a dataset of Bing Chat responses to questions posed by a ChatGPT-simulated curious user. SELF-CHECKER produced draft annotations, which human workers then checked and corrected at both the claim and the response level. On WiCE and BINGCHECK, SELF-CHECKER gives reasonable results but still trails fine-tuned SOTA models. Its value lies in working with any off-the-shelf LLM without training, which makes LLM-based verification a promising research direction.

Key points

  • Four modules plus a policy agent: the system pairs a policy agent with four components that respectively break text into claims, write search queries, pick out evidence, and counsel on the verdict. Labels range from supported and partially supported to not supported and refuted.
  • WiCE test set: SELF-CHECKER reaches 47.7 F1 and 71.5 accuracy, with evidence-retrieval F1 of 60.5. The fine-tuned T5-3B baseline scores 65.3 F1 and 77.1 accuracy.
  • BINGCHECK ablation: accuracy rises from 63.4 to 67.2 when golden claims and golden evidence are supplied. Evidence retrieval shows high recall (86–97) but low precision (about 30–33).
  • Limitations:
    • It cannot handle outdated information.
    • Chained LLM calls with majority voting make it computationally expensive.
    • Results are sensitive to the prompts used.
    • Annotation of BINGCHECK may carry subjective bias.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢MicrosoftRedmond · United States240 works · 123,537 citations🎓Iowa State UniversityAmes · United States4 works · 359 citations

Also on the byline: University of Rhode Island.

📚 Shelves 6 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works Social Sciences · 744 works Sociology and Political Science · 221 works

Cite

Cite as Miaoran Li, Baolin Peng, Michel Galley, Jianfeng Gao and Zhu Zhang. 2024. Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models. Findings of the Association for Computational Linguistics: NAACL 2024.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.findings-naacl.12

@inproceedings{li2024self,
  title = {{Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models}},
  author = {Miaoran Li, Baolin Peng, Michel Galley, Jianfeng Gao and Zhu Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: NAACL 2024},
  year = {2024},
  doi = {10.18653/v1/2024.findings-naacl.12},
  url = {https://doi.org/10.18653/v1/2024.findings-naacl.12}
}

References

42 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mubashara Akhtar, Oana Cocarascu, and Elena Simperl. 2022. Pubhealthtab: A public health table-based dataset for evidence-based fact checking. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1–16. find
  2. Firoj Alam, Stefano Cresci, Tanmoy Chakraborty, Fabrizio Silvestri, Dimiter Dimitrov, Giovanni Da San Martino, Shaden Shaar, Hamed Firooz, and Preslav Nakov. 2022. A survey on multimodal disinformation detection. In Proceedings of the 29th International Conference on Computational Linguistics, pages… find
  3. Pepa Atanasova, Alberto Barron-Cedeno, Tamer Elsayed, Reem Suwaileh, Wajdi Zaghouani, Spas Kyuchukov, Giovanni Da San Martino, and Preslav Nakov. 2018. Overview of the clef-2018 checkthat! lab on automatic identification and verification of political claims. task 1: Check-worthiness. arXiv preprint… find
  4. Alberto Barrón-Cedeño, Tamer Elsayed, Preslav Nakov, Giovanni Da San Martino, Maram Hasanain, Reem Suwaileh, Fatima Haouari, Nikolay Babulkov, Bayan Hamdan, Alex Nikolov, et al. 2020. Overview of checkthat! 2020: Automatic identification and verification of claims in social media. In Experimental IR… find
  5. 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. our card
  6. Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. Reading wikipedia to answer open-domain questions. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1870–1879. our card
  7. Shiqi Chen, Yiran Zhao, Jinghan Zhang, I-Chun Chern, Siyang Gao, Pengfei Liu, and Junxian He. 2023. FELM: Benchmarking factuality evaluation of large language models. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. find
  8. Language Technologies, pages 3670–3686, Seattle, United States. Association for Computational Linguistics. find
  9. Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou, and William Yang Wang. 2019. Tabfact: A large-scale dataset for table-based fact verification. arXiv preprint arXiv:1909.02164. our card
  10. Israa Jaradat, Pepa Gencheva, Alberto Barrón-Cedeño, Lluís Màrquez, and Preslav Nakov. 2018. Claim-Rank: Detecting check-worthy claims in Arabic and English. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 26… find
  11. I-Chun Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, and Pengfei Liu. 2023. Factool: Factuality detection in generative ai – a tool augmented framework for multi-task and multi-domain scenarios. our card
  12. Mitchell DeHaven and Stephen Scott. 2023. Bevers: A general, simple, and performant framework for automatic fact verification. arXiv preprint arXiv:2303.16974. find
  13. Kelvin Jiang, Ronak Pradeep, and Jimmy Lin. 2021. Exploring listwise evidence reasoning with t5 for fact verification. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Shor… find
  14. Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2023. Chain-of-verification reduces hallucination in large language models. our card
  15. Ryo Kamoi, Tanya Goyal, Juan Diego Rodriguez, and Greg Durrett. 2023. Wice: Real-world entailment for claims in wikipedia. arXiv preprint arXiv:2303.01432. our card
  16. Farima Fatahi Bayat, Kun Qian, Benjamin Han, Yisi Sang, Anton Belyy, Samira Khorshidi, Fei Wu, Ihab Ilyas, and Yunyao Li. 2023. FLEEK: Factual error detection and correction with evidence retrieved from external knowledge. In Proceedings of the 2023 Conference on Empirical Methods in Natural Languag… find
  17. Jiho Kim, Sungjin Park, Yeonsu Kwon, Yohan Jo, James Thorne, and Edward Choi. 2023. FactKG: Fact verification via reasoning on knowledge graphs. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16190–16206, Toronto, Canada. Ass… find
  18. Zhijiang Guo, Michael Schlichtkrull, and Andreas Vlachos. 2022. A survey on automated fact-checking. Transactions of the Association for Computational Linguistics, 10:178–206. our card
  19. Vivek Gupta, Maitrey Mehta, Pegah Nokhiz, and Vivek Srikumar. 2020. Infotabs: Inference on tables as semi-structured data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2309–2324. our card
  20. Naeemul Hassan, Fatma Arslan, Chengkai Li, and Mark Tremayne. 2017. Toward automated fact-checking: Detecting check-worthy factual claims by claimbuster. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1803–1812. find
  21. Kung-Hsiang Huang, Hou Pong Chan, and Heng Ji. 2023. Zero-shot faithful factual error correction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5660–5676, Toronto, Canada. Association for Computational Linguistics. find
  22. Robert Iv, Alexandre Passos, Sameer Singh, and Ming-Wei Chang. 2022. FRUIT: Faithfully reflecting updated information in text. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Amrith Krishna, Sebastian Riedel, and Andreas Vla… find
  23. Junyi Li, Xiaoxue Cheng, Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2023. HaluEval: A large-scale hallucination evaluation benchmark for large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6449–6464, Singapore. Association for Computa… our card
  24. Nelson F Liu, Tianyi Zhang, and Percy Liang. 2023. Evaluating verifiability in generative search engines. arXiv preprint arXiv:2304.09848. our card
  25. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural L… our card
  26. OpenAI. 2023. Gpt-4 technical report. abs/2303.08774. our card
  27. ArXiv, Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, and Preslav Nakov. 2023. Fact-checking complex claims with program-guided reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6… our card
  28. Ankur Parikh, Oscar Täckström, Dipanjan Das, and Jakob Uszkoreit. 2016. A decomposable attention model for natural language inference. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2249–2255. our card
  29. Fabio Petroni, Samuel Broscheit, Aleksandra Piktus, Patrick Lewis, Gautier Izacard, Lucas Hosseini, Jane Dwivedi-Yu, Maria Lomeli, Timo Schick, Pierre-Emmanuel Mazaré, et al. 2022. Improving wikipedia verifiability with ai. arXiv preprint arXiv:2207.06220. — [arXiv:2207.06220](https://arxiv.org/abs/2207.06220) find
  30. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21:1– 67. our card
  31. Tal Schuster, Adam Fisch, and Regina Barzilay. 2021. Get your vitamin c! robust fact verification with contrastive evidence. arXiv preprint arXiv:2103.08541. our card
  32. Amir Soleimani, Christof Monz, and Marcel Worring. 2020. Bert for evidence retrieval and claim verification. In Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14–17, 2020, Proceedings, Part II 42, pages 359–366. Springer. find
  33. Factcheck-gpt: End-to-end fine-grained document-level fact-checking and correction of llm output. find
  34. 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 reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837. our card
  35. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR). our card
  36. Xia Zeng, Amani S. Abumansour, and Arkaitz Zubiaga. 2021. Automated Fact-Checking: A Survey. ArXiv:2109.11427 [cs]. — [arXiv:2109.11427](https://arxiv.org/abs/2109.11427) find
  37. Ruochen Zhao, Xingxuan Li, Shafiq Joty, Chengwei Qin, and Lidong Bing. 2023. Verify-and-edit: A knowledge-enhanced chain-of-thought framework. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5823–5840, Toronto, Canada. Associa… our card
  38. Biru Zhu, Xingyao Zhang, Ming Gu, and Yangdong Deng. 2021. Knowledge enhanced fact checking and verification. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29:3132–3143. find
  39. James Thorne and Andreas Vlachos. 2021. Evidence-based factual error correction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3298–3309, Online. Ass… find
  40. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. Fever: a large-scale dataset for fact extraction and verification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vo… our card
  41. Nikhita Vedula and Srinivasan Parthasarathy. 2021. Face-keg: Fact checking explained using knowledge graphs. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, WSDM ’21, page 526–534, New York, NY, USA. Association for Computing Machinery. find
  42. Yuxia Wang, Revanth Gangi Reddy, Zain Muhammad Mujahid, Arnav Arora, Aleksandr Rubashevskii, Jiahui Geng, Osama Mohammed Afzal, Liangming Pan, Nadav Borenstein, Aditya Pillai, Isabelle Augenstein, Iryna Gurevych, and Preslav Nakov. 2023. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/li-2024-self-checker-plug-play-modules/