paper-with-me

Papers

Why Can Large Language Models Generate Correct Chain-of-Thoughts?

2023-10-20 · Rasul Tutunov, Antoine Grosnit, Juliusz Ziomek, Jun Wang, Haitham Bou-Ammar

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.

📄 PDF Abstract BibTeX arXiv:2310.13571

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models

2023-04-23 · Jiashuo Sun, Yi Luo, Yeyun Gong, Chen Lin 외

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

2025-03-28 · Zhanke Zhou, Zhaocheng Zhu, Xuan Li, Mikhail Galkin 외

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

2024-12-02 · Yudi Shi, Shangzhe Di, Qirui Chen, Weidi Xie

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+2

Hybrid Training for Vision-Language-Action Models

2025-10-01 · Pietro Mazzaglia, Cansu Sancaktar, Markus Peschl, Daniel Dijkman arxiv

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

2026-05-22 · Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao 외 arxiv

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, …