Information retrieval systems have long treated semantic similarity as a proxy for relevance. For constraint-sensitive queries, this proxy can fail when a document is topically close to the query but supports the opposite constraint direction, such as satisfying an attribute that should be excluded or affirming a relation that should be negated. We study this failure as constraint-violating evidence exposure and propose CoDeR, a local constraint-compatible dense retrieval method that separates topical relevance from constraint compatibility. CoDeR keeps a standard topical encoder for candidate coverage and adds a compatibility scorer, implemented as a bi-encoder, trained with lexical-polarity supervision over contrastive satisfying and violating evidences. The compatibility signal can be used to rescore topical candidates or to retrieve an auxiliary compatibility-oriented candidate set, producing a ranked document list without external Large Language Model~(LLM) calls at inference time. We evaluate CoDeR on controlled diagnostics and public negative-constraint retrieval benchmarks. Across three controlled diagnostic sets targeting antonymy, negation, and exclusion, CoDeR reduces V@2 by 20.59, 23.53, and 5.77 points relative to the strongest non-CoDeR baselines, and improves FVR by pushing the first violating document deeper in the ranking.

翻译：信息检索系统长期将语义相似性视为相关性的代理指标。对于约束敏感型查询，当文档在主题上与查询接近但支持相反的约束方向时（例如满足本应排除的属性或肯定本应否定的关系），这一代理指标可能失效。我们将此失效情况定义为违反约束的证据暴露，并提出CoDeR——一种局部约束兼容的稠密检索方法，该方法将主题相关性与约束兼容性分离。CoDeR保留标准主题编码器用于候选覆盖，并新增兼容性评分器（以双编码器实现），通过对比性满足证据与违反证据的词汇极性监督进行训练。兼容性信号可用于对主题候选进行重排序，或检索辅助的兼容性导向候选集，从而在推理阶段无需外部大型语言模型（LLM）调用即可生成排序文档列表。我们在受控诊断测试集和公开负约束检索基准上评估CoDeR。在针对反义、否定和排除的三组受控诊断测试中，相比最强的非CoDeR基线，CoDeR将V@2分别降低20.59、23.53和5.77个百分点，并通过将首个违规文档推至排序更深处来提升FVR。