Tag: chain of thought
Browse our exclusive articles!
CAP-CoT: Boosting Chain of Thought Accuracy in LLMs
Discover CAP-CoT, a novel cycle adversarial prompt method that improves accuracy, stability, and robustness in large language model reasoning.
LLM Robustness to Chain-of-Thought Perturbations Explained
Explore how large language models handle chain-of-thought perturbations and improve reasoning accuracy across diverse error types.
Trace-Based Knowledge Distillation: Accuracy vs Interpretability
Explore the impact of trace correctness on accuracy and interpretability in trace-based knowledge distillation for large language models.
Chain-of-Thought Lowers Visual Spatial Reasoning in Multimodal LLMs
Study reveals Chain-of-Thought prompting reduces visual spatial reasoning accuracy in multimodal LLMs, urging new vision-centric AI methods.
LLM Reasoning Relies on Latent States, Not Chain of Thought
Discover why LLM reasoning is driven by latent-state trajectories, challenging traditional chain-of-thought models for better AI interpretability.