5 papers
Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
Pin Qian, Su Wang, Xiaoyuan Wang +7
Cited RAG evaluation often treats visible sources as a grounding signal, but a real, topically relevant citation can still under-warrant the attached wording. We study this diagnos…
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Jian Xie, Tianhe Lin, Zilu Wang +16
Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information.…
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
Tianle Wang, Zhaoyang Wang, Guangchen Lan +4
Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with task difficulty has been hampered…
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
Yihang Chen, Pin Qian, Su Wang +4
Retrieval-Augmented Generation (RAG) is usually evaluated by whether the final answer is correct. Under knowledge conflict, this hides a key question: did the model follow retrieve…
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Guangchen Lan, Sipeng Zhang, Tianle Wang +7
As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving perfor…