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

arXiv: https://arxiv.org/abs/2512.05012 · HTML: https://mlsanity.com/paper/2512.05012/

## 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 (most cited first, 7 of 7)

- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards](https://mlsanity.com/paper/2210.12186/) (2022)
- [Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes](https://mlsanity.com/paper/2506.06506/) (2025)
- [EqualizeIR: Mitigating Linguistic Biases in Retrieval Models](https://mlsanity.com/paper/2504.07115/) (2025)
- [Discovering Biases in Information Retrieval Models Using Relevance Thesaurus as Global Explanation](https://mlsanity.com/paper/2410.03584/) (2024)

## 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.