发现引用文献未必支撑结论，提出新评测基准检测论证强度失真。
Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
- 设计对比测试集，固定引用文本，改变论述力度五维度
- 现有模型在力度校准上表现差，32.8%~36.4%的对子违反单调性
- 适合评估大模型引用合理性，推动更严格的证据评测
引用型RAG评估常将可见来源视为事实依据，但一个主题相关引用仍可能无法支撑过强论断。我们将其称为‘引用洗白’：相关来源被用作过度主张的证明。为此提出FORCEBENCH，一种对比性压力测试，用于证据力度校准。每项测试固定引用段落，沿关系、模态、范围、时间有效性、数值精确性五个维度，配对一个证据校准的陈述与一个局部力度提升的变体。理想评估者应给校准版本更高评分。头部实验使用198对经局部过滤的固定测试集。引用存在性检查本就不具信息量；即使在词元和实体重叠情况下，仍有32.8%–36.4%的对子违反单调性。四个模型裁判结果显示，通用支持提示不足以应对此压力测试（综合MVR 47.2%），而显式强调论证强度提示可降至24.5%，但仍不完美。我们公开基准、提示、输出及插件管道，供引用评估者报告单调性违规率与力度敏感性，作为常规支持度指标的补充。
原文摘要 · Abstract (English)
Cited RAG evaluation often treats visible sources as a grounding signal, but a real, topically relevant citation can still under-warrant the attached wording. We study this diagnostic failure as citation laundering: a related source is presented as warrant for an over-strong claim. We introduce FORCEBENCH, a contrastive stress test for evidence-force calibration. Each item holds a cited passage fixed and pairs an evidence-calibrated claim with a localized force-raised variant across five operational axes: relation, modality, scope, temporal validity, and numeric specificity. A calibrated evaluator should score the evidence-calibrated claim higher. Headline experiments use a fixed, locality-filtered 198-pair evaluation set. A citation-presence sanity check is uninformative by design; token and entity overlap still violate monotonicity on 32.8--36.4% of pairs. Across four reported model judges, standard generic support prompting is insufficient for this force-calibration stress test (aggregate MVR 47.2%), while explicit warrant-strength prompting lowers MVR to 24.5% but remains imperfect. We release the benchmark, prompts, outputs, and plug-in pipeline so citation evaluators can report monotonicity violation rate and force sensitivity alongside conventional support metrics.
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。