mlsanityData to 14 Oct 2026

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning

arXiv 2509.01412 ↗First posted 1 Sep 2025cs.CLcited by 0

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 26 of its 61 references that are in the map. First posted on arXiv 1 Sep 2025.

Builds on

26 of 61 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models9 Oct
  2. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models18 Aug
  3. 2023Measuring Faithfulness in Chain-of-Thought Reasoning17 Jul
  4. 2023Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models26 May
  5. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 20

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  2. 2023Let's Verify Step by Stepcited by 3,789
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  5. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  6. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  7. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  8. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
  9. 2023NISF: Neural Implicit Segmentation Functionscited by 29
  10. 2023Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniquescited by 24
  11. 2024Enhancing Blind Video Quality Assessment with Rich Quality-aware Featurescited by 19
  12. 2023Light Schr"odinger Bridgecited by 18
8 more
  1. 2023Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Modelscited by 8
  2. 2023Balancing Test Accuracy and Security in Computerized Adaptive Testingcited by 4
  3. 2024G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Imagescited by 3
  4. 2024HOIN: High-Order Implicit Neural Representationscited by 3
  5. 2024Generalize Polyp Segmentation via Inpainting across Diverse Backgrounds and Pseudo-Mask Refinementcited by 3
  6. 2024Few-Shot Object Detection with Sparse Context Transformerscited by 2
  7. 2023Underwater Sound Speed Profile Construction: A Reviewcited by 1
  8. 2024Statistical curriculum learning: An elimination algorithm achieving an oracle riskcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces
  2. 2025Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
  3. 2025The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
  4. 2026When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors
  5. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
  6. 2025Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
  7. 2025Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism
  8. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning