让智能体回答更可信：按证据程度自动调整具体性
Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems
- 将回答拆成独立陈述，逐条校准精确度
- 在LongFact数据集上将有用性提升至0.913，保留93.8%精确度
- 适合需要可信推理的对话系统和知识问答场景
智能体常因过度精确而失准：虽整体有用，但个别陈述超出证据支持。本文研究此问题为过承诺控制，提出组合选择性精确度（CSS）方法，将回答分解为若干陈述，生成更宽松的表述，并以最精确且合理的方式输出每条陈述。该方法通过局部语义退让表达不确定性，而非整体拒绝。在完整的LongFact测试和HotpotQA初步实验中，校准后的CSS显著改善了风险-效用权衡。在LongFact上，其过承诺感知有用性从0.846提升至0.913，同时保持0.938的精确度保留率。结果表明，声明级精确度控制是智能体系统中有效的不确定性接口，值得作为未来无分布验证层的目标。
原文摘要 · Abstract (English)
Agentic systems often fail not by being entirely wrong, but by being too precise: a response may be generally useful while particular claims exceed what the evidence supports. We study this failure mode as overcommitment control and introduce compositional selective specificity (CSS), a post-generation layer that decomposes an answer into claims, proposes coarser backoffs, and emits each claim at the most specific calibrated level that appears admissible. The method is designed to express uncertainty as a local semantic backoff rather than as a whole-answer refusal. Across a full LongFact run and HotpotQA pilots, calibrated CSS improves the risk-utility trade-off of fixed drafts. On the full LongFact run, it raises overcommitment-aware utility from 0.846 to 0.913 relative to the no-CSS output while achieving 0.938 specificity retention. These results suggest that claim-level specificity control is a useful uncertainty interface for agentic systems and a target for future distribution-free validity layers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。