3 papers
cs.CL2024
Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering
Haowei Du, Huishuai Zhang, Dongyan Zhao
To address the hallucination in generative question answering (GQA) where the answer can not be derived from the document, we propose a novel evidence-enhanced triplet generation f…
cs.CL2024
In-Context Learning with Reinforcement Learning for Incomplete Utterance Rewriting
Haowei Du, Dongyan Zhao
In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with…
cs.CL2024
Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answering
Haowei Du, Dongyan Zhao
Recent works have attempted to integrate external knowledge into LLMs to address the limitations and potential factual errors in LLM-generated content. However, how to retrieve the…