5 papers
Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA
Zhanli Li, Yixuan Cao, Lvzhou Luo +1
This paper introduces the task of analytical question answering over large, semi-structured document collections. We present MuDABench, a benchmark for multi-document analytical QA…
DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search
Zhanli Li, Huiwen Tian, Lvzhou Luo +2
With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonom…
The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection
Qiang Ding, Lvzhou Luo, Yixuan Cao +1
Ensuring that Large Language Models (LLMs) generate summaries faithful to a given source document is essential for real-world applications. While prior research has explored LLM fa…
AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
Lvzhou Luo, Yixuan Cao, Ping Luo
Retrieval-augmented generation improves the factual accuracy of Large Language Models (LLMs) by incorporating external context, but often suffers from irrelevant retrieved content…
Attention with Dependency Parsing Augmentation for Fine-Grained Attribution
Qiang Ding, Lvzhou Luo, Yixuan Cao +1
To assist humans in efficiently validating RAG-generated content, developing a fine-grained attribution mechanism that provides supporting evidence from retrieved documents for eve…