Why Can Large Language Models Generate Correct Chain-of-Thoughts?
This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investigate how LLMs can be effectively induced to generate a coherent chain of thoughts. To achieve this, we introduce a two-level hierarchical graphical model tailored for natural language generation. Within this framework, we establish a compelling geometrical convergence rate that gauges the likelihood of an LLM-generated chain of thoughts compared to those originating from the true language. Our findings provide a theoretical justification for the ability of LLMs to produce the correct sequence of thoughts (potentially) explaining performance gains in tasks demanding reasoning skills.
Code (0)
등록된 구현이 없습니다.
Tasks
Text GenerationSimilar Papers 제목 키워드 기반
Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstr…
Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models
Numerous applications of large language models (LLMs) rely on their ability to perform step-by-step reasoning. However, the reasoning behavior of LLMs remains poorly understood, posing challenges to research, development…
Unlocking Video-LLM via Agent-of-Thoughts Distillation
This paper tackles the problem of video question answering (VideoQA), a task that often requires multi-step reasoning and a profound understanding of spatial-temporal dynamics. While large video-language models perform w…
Language ModelingLanguage ModellingLarge Language ModelMultiple-choice+2Hybrid Training for Vision-Language-Action Models
Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful recipe for solving complex language tasks. In robotics, similar embodied CoT s…
State commitment learning: training language models to distinguish computation from memory
Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions. As a result, …