Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
By: Kaviraj Pather , Elena Hadjigeorgiou , Arben Krasniqi and more
Potential Business Impact:
Lets people fix AI's thinking steps.
Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the process is opaque, which makes verification, debugging, and control difficult in high-stakes settings. We present Vis-CoT, a human-in-the-loop framework that converts linear CoT text into an interactive reasoning graph. Users can visualize the logical flow, identify flawed steps, and intervene by pruning incorrect paths and grafting new, user-defined premises. This shifts interaction from passive observation to active collaboration, steering models toward more accurate and trustworthy conclusions. Across GSM8K and StrategyQA, Vis-CoT improves final-answer accuracy by up to 24 percentage points over non-interactive baselines. A user study also shows large gains in perceived usability and trust. Vis-CoT points to a practical path for more reliable, understandable, and collaborative reasoning by combining LLMs with targeted human oversight.
Similar Papers
Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces
Human-Computer Interaction
Helps people check AI's thinking steps faster.
Co-CoT: A Prompt-Based Framework for Collaborative Chain-of-Thought Reasoning
Computation and Language
Lets you change how AI thinks to understand it.
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
Artificial Intelligence
Checks AI's thinking to make sure it's right.