4 papers
CASTLE2026 Team WDL Technical Report
Zhengyang Li, Zhenglin Du, Yi Wen +3
The CASTLE Challenge @ EgoVis 2026 evaluates long-form egocentric video question answering over 600+ hours of multi-perspective recordings. Each four-choice question requires evide…
From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis
Yanyi Liu, Qingwen Yang, Tiezheng Guo +3
Hallucinations in Large Language Models (LLMs), defined as the generation of content inconsistent with facts or context, represent a core obstacle to their reliable deployment in c…
Augmented Runtime Collaboration for Self-Organizing Multi-Agent Systems: A Hybrid Bi-Criteria Routing Approach
Qingwen Yang, Feiyu Qu, Tiezheng Guo +2
LLM-based multi-agent systems have demonstrated significant capabilities across diverse domains. However, the task performance and efficiency are fundamentally constrained by their…
Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering
Tiezheng Guo, Chen Wang, Yanyi Liu +7
Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previou…