mlsanityData to 14 Oct 2026

Factuality and Transparency Are All RAG Needs! Self-Explaining Contrastive Evidence Re-ranking

arXiv 2512.05012 ↗First posted 4 Dec 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 4 Dec 2025.

Builds on

7 of 16 references.

References · 7

  1. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  2. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  3. 2020How Context Affects Language Models' Factual Predictionscited by 181
  4. 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 83
  5. 2025Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomescited by 6
  6. 2025EqualizeIR: Mitigating Linguistic Biases in Retrieval Modelscited by 5
  7. 2024Discovering Biases in Information Retrieval Models Using Relevance Thesaurus as Global Explanationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
  2. 2026When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification
  3. 2026Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG
  4. 2026NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains
  5. 2026Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG
  6. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
  7. 2026Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification
  8. 2026BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence