Thread of Thought Unraveling Chaotic Contexts

2023/11/15 by Yucheng Zhou, Xiubo Geng, Zhou, Yucheng +11 · 15 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2311.08734

Abstract

Large Language Models (LLMs) have ushered in a transformative era in the field of natural language processing, excelling in tasks related to text comprehension and generation. Nevertheless, they encounter difficulties when confronted with chaotic contexts (e.g., distractors rather than long irrelevant context), leading to the inadvertent omission of certain details within the chaotic context. In response to these challenges, we introduce the "Thread of Thought" (ThoT) strategy, which draws inspiration from human cognitive processes. ThoT systematically segments and analyzes extended contexts while adeptly selecting pertinent information. This strategy serves as a versatile "plug-and-play" module, seamlessly integrating with various LLMs and prompting techniques. In the experiments, we utilize the PopQA and EntityQ datasets, as well as a Multi-Turn Conversation Response dataset (MTCR) we collected, to illustrate that ThoT significantly improves reasoning performance compared to other prompting techniques.

Cited by

• More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering
• TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling
• Automatic Prompt Generation via Adaptive Selection of Prompting Techniques
• Schema for In-Context Learning
• AMELIA: A Family of Multi-task End-to-end Language Models for Argumentation
• Enhancing Retrieval Augmentation via Adversarial Collaboration
• Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding
• Robust Diagram Reasoning: A Framework for Enhancing LVLM Performance on Visually Perturbed Scientific Diagrams
• Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization
• DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Models
• MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models
• M3PO: Multimodal-Model-Guided Preference Optimization for Visual Instruction Following
• X-Ray-CoT: Interpretable Chest X-ray Diagnosis with Vision-Language Models via Chain-of-Thought Reasoning
• ContextGuard-LVLM: Enhancing News Veracity through Fine-grained Cross-modal Contextual Consistency Verification
• Coherent Multimodal Reasoning with Iterative Self-Evaluation for Vision-Language Models

Related

• Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango
• Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
• Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning
• Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
• R³ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context