Improving Attributed Text Generation of Large Language Models via Preference Learning

arXiv:2403.18381v1 Announce Type: new
Abstract: Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means to provide evidence (i.e., citations). However, current attribution methods usually focus on the retrieval stage and automatic evaluation that neglect mirroring the citation mechanisms in human scholarly writing to bolster credibility. In this paper, we address these challenges by modelling …

abstract aim arxiv attribution challenge citations cs.ai cs.cl current evidence face hallucinations however improving language language models language processing large language large language models misinformation natural natural language natural language processing processing reduce text text generation type via