In plain words: It gathers recent work on how large AI models make up facts, sorting the kinds of made-up output, ways to measure it, and fixes that reduce it. The review turns scattered studies into one map of the problem and points to open questions.
Abstract
Hallucination in a foundation model (FM) refers to the generation of content that strays from factual reality or includes fabricated information. This survey paper provides an extensive overview of recent efforts that aim to identify, elucidate, and tackle the problem of hallucination, with a particular focus on ``Large'' Foundation Models (LFMs). The paper classifies various types of hallucination phenomena that are specific to LFMs and establishes evaluation criteria for assessing the extent of hallucination. It also examines existing strategies for mitigating hallucination in LFMs and discusses potential directions for future research in this area. Essentially, the paper offers a comprehensive examination of the challenges and solutions related to hallucination in LFMs.
Vipula Rawte, Amit Sheth, Amitava Das
arXiv:2309.05922 · cs.AI, cs.CL, cs.IR · submitted Sep 12, 2023
abstract · pdf · html