7 papers · 1 filter
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…
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…
DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
Yongxin He, Shan Zhang, Yixuan Cao +2
Detecting AI-involved text is essential for combating misinformation, plagiarism, and academic misconduct. However, AI text generation includes diverse collaborative processes (AI-…
Reasoning Pattern Matters: Learning to Reason without Human Rationales
Chaoxu Pang, Yixuan Cao, Ping Luo
Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities under the widely adopted SFT+RLVR paradigm, which first performs Supervised Fine-Tuning (SFT) on hu…
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…
Document-Level Tabular Numerical Cross-Checking: A Coarse-to-Fine Approach
Chaoxu Pang, Yixuan Cao, Ganbin Zhou +2
Numerical consistency across tables in disclosure documents is critical for ensuring accuracy, maintaining credibility, and avoiding reputational and economic risks. Automated tabu…