中文
相关论文

相关论文: Whiteboard-of-Thought: Thinking Step-by-Step Acros…

200 篇论文

Recent progress in multimodal reasoning has been significantly advanced by textual Chain-of-Thought (CoT), a paradigm where models conduct reasoning within language. This text-centric approach, however, treats vision as a static, initial…

计算机视觉与模式识别 · 计算机科学 2025-07-04 Zhaochen Su , Peng Xia , Hangyu Guo , Zhenhua Liu , Yan Ma , Xiaoye Qu , Jiaqi Liu , Yanshu Li , Kaide Zeng , Zhengyuan Yang , Linjie Li , Yu Cheng , Heng Ji , Junxian He , Yi R. Fung

Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in…

计算与语言 · 计算机科学 2023-12-05 Shunyu Yao , Dian Yu , Jeffrey Zhao , Izhak Shafran , Thomas L. Griffiths , Yuan Cao , Karthik Narasimhan

Recently, Chain-of-Thought (CoT) prompting has delivered success on complex reasoning tasks, which aims at designing a simple prompt like ``Let's think step by step'' or multiple in-context exemplars with well-designed rationales to elicit…

计算与语言 · 计算机科学 2024-06-04 Jianing Wang , Qiushi Sun , Xiang Li , Ming Gao

Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images.…

人工智能 · 计算机科学 2023-12-15 Liqi He , Zuchao Li , Xiantao Cai , Ping Wang

A large-scale vision and language model that has been pretrained on massive data encodes visual and linguistic prior, which makes it easier to generate images and language that are more natural and realistic. Despite this, there is still a…

计算机视觉与模式识别 · 计算机科学 2025-02-20 Hao Huang , Shuaihang Yuan , Yu Hao , Congcong Wen , Yi Fang

The reasoning performance of Large Language Models (LLMs) on a wide range of problems critically relies on chain-of-thought prompting, which involves providing a few chain of thought demonstrations as exemplars in prompts. Recent work,…

计算与语言 · 计算机科学 2025-01-08 Sijia Chen , Baochun Li , Di Niu

Large language models can perform various reasoning tasks by using chain-of-thought prompting, which guides them to find answers through step-by-step demonstrations. However, the quality of the prompts depends on the demonstrations given to…

计算与语言 · 计算机科学 2023-02-02 Zhihong Shao , Yeyun Gong , Yelong Shen , Minlie Huang , Nan Duan , Weizhu Chen

Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to external modi operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models' (LLMs) reasoning…

计算与语言 · 计算机科学 2024-06-04 Bilgehan Sel , Ahmad Al-Tawaha , Vanshaj Khattar , Ruoxi Jia , Ming Jin

Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thinking'' really helpful? To analyze this, we conducted a…

Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques.…

计算与语言 · 计算机科学 2026-03-03 Jinyang Wu , Mingkuan Feng , Guocheng Zhai , Shuai Zhang , Zheng Lian , Fangrui Lv , Pengpeng Shao , Ruihan Jin , Zhengqi Wen , Jianhua Tao

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks but their performance in complex logical reasoning tasks remains unsatisfactory. Although some prompting methods, such as Chain-of-Thought, can…

计算与语言 · 计算机科学 2025-02-10 Tongxuan Liu , Wenjiang Xu , Weizhe Huang , Yuting Zeng , Jiaxing Wang , Xingyu Wang , Hailong Yang , Jing Li

Multi-modality promises to unlock further uses for large language models. Recently, the state-of-the-art language model GPT-4 was enhanced with vision capabilities. We carry out a prompting evaluation of GPT-4V and five other baselines on…

计算与语言 · 计算机科学 2023-12-20 Mukul Singh , José Cambronero , Sumit Gulwani , Vu Le , Gust Verbruggen

Recently, there has been significant progress in teaching language models to perform step-by-step reasoning to solve complex numerical reasoning tasks. Chain-of-thoughts prompting (CoT) is by far the state-of-art method for these tasks. CoT…

计算与语言 · 计算机科学 2023-10-24 Wenhu Chen , Xueguang Ma , Xinyi Wang , William W. Cohen

As language models have become increasingly successful at a wide array of tasks, different prompt engineering methods have been developed alongside them in order to adapt these models to new tasks. One of them is Tree-of-Thoughts (ToT), a…

人机交互 · 计算机科学 2024-09-04 Alan Boyle , Isha Gupta , Sebastian Hönig , Lukas Mautner , Kenza Amara , Furui Cheng , Mennatallah El-Assady

Human beings naturally utilize multiple reasoning modalities to learn and solve logical problems, i.e., different representational formats such as natural language, code, and symbolic logic. In contrast, most existing LLM-based approaches…

计算与语言 · 计算机科学 2025-06-11 Tong Zheng , Lichang Chen , Simeng Han , R. Thomas McCoy , Heng Huang

Reasoning methods, best exemplified by the well-known Chain-of-Thought (CoT), empower the reasoning abilities of Large Language Models (LLMs) by eliciting them to solve complex tasks in a step-by-step manner. Although they are achieving…

计算与语言 · 计算机科学 2024-06-24 Leonardo Ranaldi , Giulia Pucci , Federico Ranaldi , Elena Sofia Ruzzetti , Fabio Massimo Zanzotto

Humans draw to facilitate reasoning: we draw auxiliary lines when solving geometry problems; we mark and circle when reasoning on maps; we use sketches to amplify our ideas and relieve our limited-capacity working memory. However, such…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Yushi Hu , Weijia Shi , Xingyu Fu , Dan Roth , Mari Ostendorf , Luke Zettlemoyer , Noah A Smith , Ranjay Krishna

The chain-of-thought technique has been received well in multi-modal tasks. It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts. However, human thought processes…

人工智能 · 计算机科学 2024-04-09 Juncheng Yang , Zuchao Li , Shuai Xie , Wei Yu , Shijun Li , Bo Du

Chain-of-thought prompting (e.g., "Let's think step-by-step") primes large language models to verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic performance gains, benefits appear to emerge only for…

计算与语言 · 计算机科学 2024-04-17 Liunian Harold Li , Jack Hessel , Youngjae Yu , Xiang Ren , Kai-Wei Chang , Yejin Choi

This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT)…

计算与语言 · 计算机科学 2025-06-10 Lennart Meincke , Ethan Mollick , Lilach Mollick , Dan Shapiro