SOURCE-LINKED INTELLIGENCE

Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided evidence. When evidence is insufficient, it is desirable that models abstain rather than confidently generating unsupported answers. Existing abstention methods rely on uncertainty estimation or evidence sufficiency checks, but neither tests whether the reasoning process for generation, driven by the interaction of provided evidence and the model's internal memory parameters, is actually grounded in the evidence. A key contributing factor is that entity mentions in context activate memorised assoc

Read original source ↗ Open in workspace

recordType

paper

region

Global