Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution Paper • 2603.05308 • Published Mar 5 • 2
RAGLens Collection A lightweight hallucination detector that uses sparse autoencoders to identify, explain, and mitigate unfaithful RAG outputs • 4 items • Updated 13 days ago • 1
Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders Paper • 2512.08892 • Published Dec 9, 2025 • 1
Toward Reliable Biomedical Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models Paper • 2505.14599 • Published May 20, 2025 • 2
RAG-Gym: Optimizing Reasoning and Search Agents with Process Supervision Paper • 2502.13957 • Published Feb 19, 2025 • 1