How Language Model Hallucinations Can Snowball | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A collection of research papers on LLMs.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

How Language Model Hallucinations Can Snowball

Muru Zhang, Ofir Press, William Merrill, Alisa Liu, Noah A. Smith . Arxiv 2023 – 59 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Applications Compositional Generalization Datasets Interdisciplinary Approaches Model Architecture Multimodal Semantic Representation

A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs, but we hypothesize that in some cases, when justifying previously generated hallucinations, LMs output false claims that they can separately recognize as incorrect. We construct three question-answering datasets where ChatGPT and GPT-4 often state an incorrect answer and offer an explanation with at least one incorrect claim. Crucially, we find that ChatGPT and GPT-4 can identify 67% and 87% of their own mistakes, respectively. We refer to this phenomenon as hallucination snowballing: an LM over-commits to early mistakes, leading to more mistakes that it otherwise would not make.

Similar Work