Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG

• URL: http://arxiv.org/abs/2606.01482v1
• Date: Sun, 31 May 2026 22:54:44 GMT
• Title: Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
• Abstract summary: We introduce Contrastive Evidence Rationale Attention (CERA), the first retrieval framework to employ subjectivity-based hard negative selection.<n>CERA fine-tunes a dense retriever using two training objectives: triplet-based contrastive learning and interpretable attention alignment.
• Score: 20.048041581496896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ensuring factuality and interpretability in RAG remains an open and urgent problem. We introduce Contrastive Evidence Rationale Attention (CERA), the first retrieval framework to employ subjectivity-based hard negative selection and inject an evidential inductive bias into contrastive learning through an auxiliary attention alignment loss. CERA fine-tunes a dense retriever using two training objectives: triplet-based contrastive learning and interpretable attention alignment, which supervises CLS-to-token attention using a part-of-speech-weighted masking distribution over human-annotated factual rationales as evidence signals. Experiments on a large corpus of clinical trial reports demonstrate that the subjectivity-based hard negative selection substantially improves retrieval effectiveness compared to both Contriever and hard negative selection baselines. Furthermore, rationale alignment improves faithfulness while maintaining competitive retrieval performance, supporting the hypothesis that attention can serve as a more faithful explanation of model behavior when guided by human rationales. Moving beyond topical similarity, CERA enables the retriever to identify the specific tokens that constitute supporting evidence, promoting more interpretable evidence selection in RAG systems.

Related papers

• Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems [55.04168927059962]
  Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity.<n>We introduce BRIGHT-Pro, an expert-annotated benchmark that expands each query with multi-aspect gold evidence.<n>We also construct RTriever- Synth, an aspect-decomposed synthetic corpus that generates complementary positives and positive-conditioned hard negatives.
  arXiv  Detail & Related papers  (2026-05-05T17:42:50Z)
• Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification [77.51622646061314]
  ReID-R is proposed as a novel reasoning-driven paradigm that achieves explicit identity understanding and reasoning.<n>Experiments on multiple ReID benchmarks demonstrate that ReID-R achieves competitive identity discrimination as superior methods.
  arXiv  Detail & Related papers  (2026-04-21T08:24:07Z)
• Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification [52.784239635604735]
  VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images.<n>Existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability.<n>We propose a Causal Bootstrapped Alignment framework that explicitly exploits inherent video priors.
  arXiv  Detail & Related papers  (2026-04-17T02:15:59Z)
• Enabling and Inhibitory Pathways of Students' AI Use Concealment Intention in Higher Education: Evidence from SEM and fsQCA [0.0]
  The study contributes to the literature by conceptualising concealment as a distinct behavioural outcome.<n> Practical implications emphasise the need for clear institutional policies, destigmatisation of appropriate AI use, and the cultivation of supportive learning environments.
  arXiv  Detail & Related papers  (2026-04-13T04:35:07Z)
• Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment [97.55382322103986]
  Hit-RAG is a multi-stage preference alignment framework designed to resolve cognitive bottlenecks.<n>Our approach systematically refines the utilization of external evidence via three distinct stages.
  arXiv  Detail & Related papers  (2026-03-07T04:05:27Z)
• Factuality and Transparency Are All RAG Needs! Self-Explaining Contrastive Evidence Re-ranking [0.2864713389096699]
  This extended abstract introduces Self-Explaining Contrastive Evidence Re-Ranking (CER)<n>CER restructures retrieval around factual evidence by fine-tuning embeddings with contrastive learning and generating token-level attribution rationales for each retrieved passage.<n>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.
  arXiv  Detail & Related papers  (2025-12-04T17:24:35Z)
• In-context Contrastive Learning for Event Causality Identification [26.132189768472067]
  Event Causality Identification aims at determining the existence of a causal relation between two events. Recent prompt learning-based approaches have shown promising improvements on the ECI task. This paper proposes an In-Context Contrastive Learning model that utilizes contrastive learning to enhance the effectiveness of both positive and negative demonstrations.
  arXiv  Detail & Related papers  (2024-05-17T03:32:15Z)
• Generalization Bounds for Robust Contrastive Learning: From Theory to Practice [20.805320268190936]
  We develop theories to identify which components in the unsupervised training can help improve the robust supervised loss.<n>Besides the adversarial contrastive loss, we reveal that the benign one, along with a global divergence between benign and adversarial examples can also improve robustness.
  arXiv  Detail & Related papers  (2023-11-16T08:39:58Z)
• Fairness and robustness in anti-causal prediction [73.693135253335]
  Robustness to distribution shift and fairness have independently emerged as two important desiderata required of machine learning models. While these two desiderata seem related, the connection between them is often unclear in practice. By taking this perspective, we draw explicit connections between a common fairness criterion - separation - and a common notion of robustness.
  arXiv  Detail & Related papers  (2022-09-20T02:41:17Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.