This extended abstract introduces Self-Explaining Contrastive Evidence Re-Ranking (CER), a novel method that restructures retrieval around factual evidence by fine-tuning embeddings with contrastive learning and generating token-level attribution rationales for each retrieved passage. Hard negatives are automatically selected using a subjectivity-based criterion, forcing the model to pull factual rationales closer while pushing subjective or misleading explanations apart. As a result, the method creates an embedding space explicitly aligned with evidential reasoning. We evaluated our method on clinical trial reports, and initial experimental results show that CER improves retrieval accuracy, mitigates the potential for hallucinations in RAG systems, and provides transparent, evidence-based retrieval that enhances reliability, especially in safety-critical domains.

翻译：本扩展摘要介绍了自解释对比证据重排序（CER）这一新方法，该方法通过对比学习微调嵌入向量并为每个检索段落生成词级归因解释，围绕事实证据重构检索过程。基于主观性准则自动选择困难负例，迫使模型拉近事实性解释，同时推离主观或误导性解释。因此，该方法构建了与证据推理明确对齐的嵌入空间。我们在临床试验报告上评估了该方法，初步实验结果表明：CER提升了检索准确率，缓解了RAG系统中可能产生的幻觉问题，并提供透明、基于证据的检索机制，显著增强了可靠性，尤其在安全关键领域。