reasoning accuracy
This relates to the correctness and reliability of an AI system's predictions or conclusions based on its reasoning processes. High reasoning accuracy is essential for trustworthiness in applications like diagnostics and autonomous systems.
- Activation-Guided Consensus Merging for Large Language Models
- Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding
- Inference-Time Hyper-Scaling with KV Cache Compression
- Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
- SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
- Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training