让大模型推理更可信，只采纳有证据支持的猜想。
EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning
- 用证据锁库机制筛选中间假设，确保每步推理都有据可依。
- 在NarraCrime等数据集上提升任务准确率与证据忠实度。
- 适合需要高可靠性推理的长篇故事分析场景。
大型语言模型在处理非交互式长篇叙事时，常产生流畅但缺乏依据的结论。核心问题在于未经证实的中间假设会进入推理路径并污染后续判断，尤其当证据分散于文本各处时。为此，我们提出EVAR——一种面向预算约束的叙事推理中证据验证假设准入框架。EVAR首先将叙事转化为带来源链接的原子命题不可变证据库，并根据未解缺口和不确定性信号分配实例化推理预算。在精炼阶段，直接为未解缺口提出候选假设，构建假设条件下的验证挑战，并在锁定的证据库中验证每个候选：被支持的假设进入支撑答案状态，无法验证的被隔离，矛盾的则被丢弃。基于充分性停止机制进一步避免冗余精炼。在NarraCrime及多个公开推理基准上的实验表明，EVAR在保持可控推理成本的同时，显著提升了任务表现与证据忠实度。
原文摘要 · Abstract (English)
Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central failure mode is that unsupported intermediate hypotheses can enter the reasoning trajectory and contaminate subsequent inference, especially when evidence is scattered across distant parts of the story. To address this problem, we propose EVAR, an evidence-validated hypothesis admission framework for budget-aware narrative reasoning. EVAR first compiles the narrative into an immutable evidence store of source-linked atomic claims and assigns an instance-specific inference budget from unresolved gaps and uncertainty signals. During refinement, EVAR directly proposes candidate hypotheses for unresolved gaps, constructs hypothesis-conditioned validation challenges, and verifies each candidate against the locked store before admission: supported hypotheses enter the answer-supporting state, unverifiable ones are quarantined, and contradictory ones are discarded. A sufficiency-based stopping mechanism further avoids unnecessary refinement. Experiments on NarraCrime and multiple public reasoning benchmarks show that EVAR improves both task performance and evidence faithfulness while maintaining controllable inference cost.
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。