WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning
Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages. In an incident report, the operating condition, design flaw, and missed safety check that jointly explain a disaster may appear dozens of sections apart; in a novel, a character's true motive may surface only through scenes far removed from the moment it becomes relevant. This source-internal evidence integration is central to real-world long-document analysis, yet existing benchmarks largely sidestep it. Needle probes, planted facts, and
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 45%wbopan/flashtrace →
- LinkedLinked via arxiv author · 85%Zixin Chen →
“WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Yipeng Liu →
“WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Haobo Li →
“WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Rui Sheng →
“WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Jianhong Tu →
“WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Xiaodong Deng →
“WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning”
- LinkedLinked via arxiv author · 85%Fei Huang →
“WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning”