63 citations · 82 across the 16 of their papers we have counts for
4 papers · 1 filter
KEEP-Bench: Evaluating Evidence Preservation in Context Compression
Ziqing Man, Di Wu, Jia-Chen Gu +3
Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader…
Lean Graph Search for Formal Theorem Proving
Yihan Xu, Jia-Chen Gu, Junyi Zhang +7
Retrieving relevant lemmas is crucial for formal theorem proving, enabling provers to build machine-checkable proofs from established mathematical results. Recent retrieval systems…
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
Di Wu, Zixiang Ji, Asmi Kawatkar +4
Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure m…
Open-Domain Safety Policy Construction
Di Wu, Siyue Liu, Zixiang Ji +4
Moderation layers are increasingly a core component of many products built on user- or model-generated content. However, drafting and maintaining domain-specific safety policies re…