2 papers
cs.CL2024
Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation
Yuxin Liang, Zhuoyang Song, Hao Wang +1
We evaluate the ability of Large Language Models (LLMs) to discern and express their internal knowledge state, a key factor in countering factual hallucination and ensuring reliabl…
cs.CL2023
UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective
Ping Yang, Junyu Lu, Ruyi Gan +4
We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition…