Towards Mitigating LLM Hallucination via Self Reflection

By Ziwei Ji, Tiezheng Yu, Yan Xu, Nayeon Lee, Etsuko Ishii, Pascale Fung. Conference on Empirical Methods in Natural Language Processing, 2023

496 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/aa7e3b2b88ae3b434e3d5a343c7e3109c9d48ea8

Citations in the corpus

• From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2024, unknown): “Besides, Shi et al. (2024) evaluate metrics such as position bias and percent agreement in question-answering tasks.”
• RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation (2025, unknown): “RAS integrates theme-aware retrieval, dynamic KG construction, and self-refinement (Ji et al., 2023; Asai et al., 2023; Lyu et al., 2024b) to comprehensively prepare knowledge for challenging questions.”