A curated list of research related to fact-checking, particularly fact-checking AI-generated outputs 🤖 ⚖️
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models by B. Wang et al. (20 June 2023)
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model by K. Li et al. (6 June 2023)
- AmbiFC: Fact-checking ambiguous claims with evidence by M. Glockner et al. (31 May 2023)
- Do Language Models Know When They're Hallucinating References? by A. Agrawal (29 May 2023)
- AlignScore: Evaluating Factual Consistency with a Unified Alignment Function by Yuheng Zha et al. (26 May 2023)
- FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation by Sewon Min et al. (23 May 2023)
- How Language Model Hallucinations Can Snowball by Zhang Muru et al. (22 May 2023)
- LM vs LM: Detecting Factual Errors via Cross Examination by Roi Cohen et al. (22 May 2023)
- Complex Claim Verification with Evidence Retrieved in the Wild by Jifan Chen et al. (19 May 2023)
- The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who by Michael Schlichtkrull et al. (27 April 2023)
- PRs are welcome
If you're interested in discussing fact-checking & hallucinations, we have a Discord server: