Cover Image

When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Shiwei, Sritharan, Niruthikka, Wen, Xiaolin, Zhang, Chenxi, Wang, Xingbo, Wang, Yong
Format:	Preprint
Published:	2026
Subjects:	Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
by: Pang, Rock Yuren, et al.
Published: (2025)

Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
by: Wang, Yu, et al.
Published: (2024)

InconLens: Interactive Visual Diagnosis of Behavioral Inconsistencies in LLM-based Agentic Systems
by: Yan, Shuo, et al.
Published: (2026)

Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations
by: Park, Eunkyu, et al.
Published: (2025)

A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning
by: Hu, Lijie, et al.
Published: (2024)

InsightLens: Augmenting LLM-Powered Data Analysis with Interactive Insight Management and Navigation
by: Weng, Luoxuan, et al.
Published: (2024)

From Static to Interactive: Authoring Interactive Visualizations via Natural Language
by: Liu, Can, et al.
Published: (2026)

Qualitative Study for LLM-assisted Design Study Process: Strategies, Challenges, and Roles
by: Ruan, Shaolun, et al.
Published: (2025)

ConSearcher: Supporting Conversational Information Seeking in Online Communities with Member Personas
by: Wu, Shiwei, et al.
Published: (2026)

HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
by: Nguyen, Tin, et al.
Published: (2025)

Interacting with Thoughtful AI
by: Liu, Xingyu Bruce, et al.
Published: (2025)

When Scaffolding Breaks: Investigating Student Interaction with LLM-Based Writing Support in Real-Time K-12 EFL Classrooms
by: Myung, Junho, et al.
Published: (2025)

GlyphWeaver: Unlocking Glyph Design Creativity with Uniform Glyph DSL and AI
by: Liu, Can, et al.
Published: (2025)

Understanding Stakeholders' Perceptions and Needs Across the LLM Supply Chain
by: Balayn, Agathe, et al.
Published: (2024)

PrettiSmart: Visual Interpretation of Smart Contracts via Simulation
by: Wen, Xiaolin, et al.
Published: (2024)

QueryGenie: Making LLM-Based Database Querying Transparent and Controllable
by: Chen, Longfei, et al.
Published: (2025)

LessonPlanner: Assisting Novice Teachers to Prepare Pedagogy-Driven Lesson Plans with Large Language Models
by: Fan, Haoxiang, et al.
Published: (2024)

Large Language Models have Chain-of-Affect
by: Xu, Junjie, et al.
Published: (2025)

SciDaSynth: Interactive Structured Data Extraction from Scientific Literature with Large Language Model
by: Wang, Xingbo, et al.
Published: (2024)

ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health Communities
by: Wu, Shiwei, et al.
Published: (2024)

IntelliCircos: A Data-driven and AI-powered Authoring Tool for Circos Plots
by: Gu, Mingyang, et al.
Published: (2025)

SCSimulator: An Exploratory Visual Analytics Framework for Partner Selection in Supply Chains through LLM-driven Multi-Agent Simulation
by: Gao, Shenghan, et al.
Published: (2026)

Anchorage: Visual Analysis of Satisfaction in Customer Service Videos via Anchor Events
by: Wong, Kam Kwai, et al.
Published: (2023)

MI 2 MI: Training Dyad with Collaborative Brain-Computer Interface and Cooperative Motor Imagery Tasks for Better BCI Performance
by: Cheng, Shiwei, et al.
Published: (2024)

ReVis: Towards Reusable Image-Based Visualizations with MLLMs
by: Wen, Xiaolin, et al.
Published: (2026)

Trinity: Synchronizing Verbal, Nonverbal, and Visual Channels to Support Academic Oral Presentation Delivery
by: Wu, Yuchen, et al.
Published: (2024)

An Empirical Exploration of Trust Dynamics in LLM Supply Chains
by: Balayn, Agathe, et al.
Published: (2024)

"Do I Trust the AI?" Towards Trustworthy AI-Assisted Diagnosis: Understanding User Perception in LLM-Supported Reasoning
by: Xu, Yuansong, et al.
Published: (2026)

Envisage: Towards Expressive Visual Graph Querying
by: Wen, Xiaolin, et al.
Published: (2025)

DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors
by: Sheng, Rui, et al.
Published: (2026)

Android in the Zoo: Chain-of-Action-Thought for GUI Agents
by: Zhang, Jiwen, et al.
Published: (2024)

WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy Reasoning
by: Li, Yuxuan, et al.
Published: (2026)

Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces
by: Zhou, Runtao, et al.
Published: (2025)

iToT: An Interactive System for Customized Tree-of-Thought Generation
by: Boyle, Alan, et al.
Published: (2024)

ComPeer: A Generative Conversational Agent for Proactive Peer Support
by: Liu, Tianjian, et al.
Published: (2024)

PonziLens+: Visualizing Bytecode Actions for Smart Ponzi Scheme Identification
by: Wen, Xiaolin, et al.
Published: (2024)

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking
by: Liu, Shunyu, et al.
Published: (2025)

Wearable AR for Restorative Breaks: How Interactive Narrative Experiences Support Relaxation for Young Adults
by: Wang, Jindu, et al.
Published: (2026)

Agentic Reasoning and Refinement through Semantic Interaction
by: Tang, Xuxin, et al.
Published: (2025)

LLM-based In-situ Thought Exchanges for Critical Paper Reading
by: Fang, Xinrui, et al.
Published: (2025)