6 papers
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…
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…
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…
Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting
Haowei Du, Dinghao Zhang, Chen Li +2
Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, which is crucial to edit the incomplete utterance, and introduce words from…
Relation-Aware Question Answering for Heterogeneous Knowledge Graphs
Haowei Du, Quzhe Huang, Chen Li +3
Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answer entity in a knowledge graph (KG), which requires multiple steps of reasoning. Existing retrieval-based app…
From Simple to Complex: A Progressive Framework for Document-level Informative Argument Extraction
Quzhe Huang, Yanxi Zhang, Dongyan Zhao
Document-level Event Argument Extraction (EAE) requires the model to extract arguments of multiple events from a single document. Considering the underlying dependencies between th…