claim-analysis

提出 RIVER 框架，将 LLM 多智能体交互分解为原子主张，评估收敛、探索与保留三个信息动态维度，并在 40 个新闻生成案例上比较五种交互策略的信息流动机制。

The paper introduces ClaimProbe, a claim-level audit framework to detect hallucinations and misattributions in deep research reports, and ClaimWriter, a hierarchical writer that reduces hallucinations by up to 4.5 times while improving fact recall.

This paper formalizes a claim-replay layer for AI evaluation artifacts and censuses evaluation units, finding that most stop before deterministic inference due to missing historical evidence or semantic grounding.