Mitigating LLM Hallucinations via Conformal Abstention

arXiv:2405.01563v1 Announce Type: new
Abstract: We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of resorting to possibly "hallucinating" a non-sensical or incorrect answer. Building on earlier approaches that use self-consistency as a more reliable measure of model confidence, we propose using the LLM itself to self-evaluate the similarity between each of its sampled responses for a given query. We then …

abstract arxiv building cs.ai cs.cl cs.lg domain general hallucinations language language model large language large language model llm llm hallucinations type via