Hallucination Diversity-Aware Active Learning for Text Summarization

arXiv:2404.01588v1 Announce Type: cross
Abstract: Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper …

abstract active learning annotations arxiv cs.ai cs.cl cs.lg diversity focus generate hallucination hallucinations human identify language language models large language large language models llm llms summarization text text summarization type