Survey of Hallucination in Large Language Models, Ziqi Ji, Nayeon Lee, Pang Wei Koh, Shangyu Tong, Raghuveer Thirukovalluru, Chauncey Wang, Faisal Radwan, Sohee Park, Sana Malik, Xiang Ren, H. Andrew Schwartz, 2023ACM Computing Surveys (CSUR), Vol. 56 (Association for Computing Machinery (ACM))DOI: 10.1145/3613694 - Comprehensive overview of hallucination causes, detection, and mitigation strategies in LLMs.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela, 2020Advances in Neural Information Processing Systems, Vol. 33 (Curran Associates, Inc.)DOI: 10.48550/arXiv.2005.11401 - Presents Retrieval-Augmented Generation (RAG), a fundamental approach for grounding LLMs with external knowledge, which is a core technique for external verification.
Measuring and Improving Factual Consistency Using Natural Language Inference, Sean Welleck, Samira Paranjape, Jason Baldridge, Yejin Choi, 2019Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (Association for Computational Linguistics)DOI: 10.18653/v1/D19-1406 - Discusses how Natural Language Inference (NLI) can be used to measure and improve the factual consistency of generated text, directly applicable to evidence comparison.