CoRA

Researchers propose Conditional Retrieval Alignment (CoRA), a gradient-free framework that converts a frozen encoder into a task-conditioned retriever for on-device in-context learning, using closed-f…

Researchers introduced CoRA, a GRPO-based reinforcement learning framework that aligns LLM confidence with rationale quality in chain-of-thought reasoning. Across MedQA, MathQA, and OpenBookQA, CoRA r…