Factuality and Transparency Are All RAG Needs! Self-Explaining Contrastive Evidence Re-ranking
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningSimilar Papers 제목 키워드 기반
Contrastive Explanations for Explaining Model Adaptations
Many decision making systems deployed in the real world are not static - a phenomenon known as model adaptation takes place over time. The need for transparency and interpretability of AI-based decision models is widely …
Decision MakingmodelC-SENN: Contrastive Self-Explaining Neural Network
In this study, we use a self-explaining neural network (SENN), which learns unsupervised concepts, to acquire concepts that are easy for people to understand automatically. In concept learning, the hidden layer retains v…
Autonomous DrivingContrastive LearningPruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
To mitigate the hallucination problem in large language models, DoLa exploits early exit logits from the same model as a contrastive prior. However, we found that these early exit logits tend to be flat, low in magnitude…
Towards Transparent Robotic Planning via Contrastive Explanations
Providing explanations of chosen robotic actions can help to increase the transparency of robotic planning and improve users' trust. Social sciences suggest that the best explanations are contrastive, explaining not just…
Improving Factuality of Abstractive Summarization via Contrastive Reward Learning
Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates r…
Abstractive Text SummarizationContrastive Learning