Tag: LLM reasoning
Browse our exclusive articles!
Absurd World: Benchmarking LLM Logical Reasoning Skills
Discover Absurd World, a novel framework to test and improve large language models' logical reasoning with absurd yet coherent scenarios.
Enhancing LLM Reasoning with Dynamic Persona Polylogues
Explore how dynamic persona vectors improve reasoning and accuracy in large language models through real-time monitoring and intervention.
Adaptive Negative Reinforcement Boosts LLM Reasoning Accuracy
Discover how Adaptive Negative Sample Reinforcement enhances Large Language Models by balancing error correction and reasoning diversity in RLVR training.
CASPO: Boosting Reliability in Reasoning Large Language Models
Discover how CASPO enhances reasoning reliability in LLMs with confidence-aware alignment and efficient inference for accurate AI outputs.
LLM Reasoning Reveals Myopic Planning in Search Trees
Study uncovers shallow search depth and myopic planning in LLMs, highlighting key differences from human decision-making strategies.