English
Related papers

Related papers: Fine-Tuning on Diverse Reasoning Chains Drives Wit…

200 papers

Despite the remarkable reasoning performance, eliciting the long chain-of-thought (CoT) ability in large language models (LLMs) typically requires costly reinforcement learning or supervised fine-tuning on high-quality distilled data. We…

Computation and Language · Computer Science 2025-05-26 Zekai Zhao , Qi Liu , Kun Zhou , Zihan Liu , Yifei Shao , Zhiting Hu , Biwei Huang

Reasoning based on Large Language Models (LLMs) has garnered increasing attention due to outstanding performance of these models in mathematical and complex logical tasks. Beginning with the Chain-of-Thought (CoT) prompting technique,…

Artificial Intelligence · Computer Science 2025-11-27 Yuto Suzuki , Farnoush Banaei-Kashani

While Long Chain-of-Thought (CoT) reasoning significantly improves Large Language Models (LLMs) performance on complex reasoning tasks, the substantial computational and memory costs of generating long CoT sequences limit their efficiency…

Artificial Intelligence · Computer Science 2026-02-03 Liang Zhang , Yu Zhao , Longyue Wang , Tianqi Shi , Weihua Luo , Kaifu Zhang , Jinsong Su

Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xuanlang Dai , Yujie Zhou , Long Xing , Jiazi Bu , Xilin Wei , Yuhong Liu , Beichen Zhang , Kai Chen , Yuhang Zang

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…

Computation and Language · Computer Science 2025-05-09 Zayne Sprague , Fangcong Yin , Juan Diego Rodriguez , Dongwei Jiang , Manya Wadhwa , Prasann Singhal , Xinyu Zhao , Xi Ye , Kyle Mahowald , Greg Durrett

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Computation and Language · Computer Science 2024-08-08 Xinyi Wang , Lucas Caccia , Oleksiy Ostapenko , Xingdi Yuan , William Yang Wang , Alessandro Sordoni

Large language models (LLMs) demonstrate significant reasoning capabilities, particularly through long chain-of-thought (CoT) processes, which can be elicited by reinforcement learning (RL). However, prolonged CoT reasoning presents…

Computation and Language · Computer Science 2025-12-29 Haoyuan Wu , Xueyi Chen , Rui Ming , Jilong Gao , Shoubo Hu , Zhuolun He , Bei Yu

Multi-step reasoning ability of large language models is crucial in tasks such as math and tool utilization. Current researches predominantly focus on enhancing model performance in these multi-step reasoning tasks through fine-tuning with…

Computation and Language · Computer Science 2024-10-23 Yuli Qiu , Jiashu Yao , Heyan Huang , Yuhang Guo

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…

Computation and Language · Computer Science 2024-06-04 Bilgehan Sel , Ahmad Al-Tawaha , Vanshaj Khattar , Ruoxi Jia , Ming Jin

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

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,…

Computation and Language · Computer Science 2025-01-08 Sijia Chen , Baochun Li , Di Niu

Chain-of-thought (CoT) decoding enables language models to improve reasoning performance at the cost of high generation latency in decoding. Recent proposals have explored variants of contemplation tokens, a term we introduce that refers to…

Computation and Language · Computer Science 2024-12-18 Jeffrey Cheng , Benjamin Van Durme

By extending the advantage of chain-of-thought (CoT) reasoning in human-like step-by-step processes to multimodal contexts, multimodal CoT (MCoT) reasoning has recently garnered significant research attention, especially in the integration…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yaoting Wang , Shengqiong Wu , Yuecheng Zhang , Shuicheng Yan , Ziwei Liu , Jiebo Luo , Hao Fei

Large language models (LLMs) are documented to struggle in settings that require complex reasoning. Nevertheless, instructing the model to break down the problem into smaller reasoning steps, or ensembling various generations through…

Computation and Language · Computer Science 2024-02-27 Ranjita Naik , Varun Chandrasekaran , Mert Yuksekgonul , Hamid Palangi , Besmira Nushi

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in tasks involving audio perception and understanding, such as speech recognition and audio captioning. However, their reasoning capabilities - critical for…

Sound · Computer Science 2025-01-14 Ziyang Ma , Zhuo Chen , Yuping Wang , Eng Siong Chng , Xie Chen

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to move beyond fast System-1 responses and engage in deliberative System-2 reasoning. However, this comes at the cost of significant inefficiency due to verbose…

Computation and Language · Computer Science 2025-06-03 Xiaoqiang Wang , Suyuchen Wang , Yun Zhu , Bang Liu

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Computation and Language · Computer Science 2025-11-04 Sriram Balasubramanian , Samyadeep Basu , Soheil Feizi

Chain of Thought (CoT) was introduced in recent research as a method for improving step-by-step reasoning in Large Language Models. However, CoT has limited applications such as its need for hand-crafted few-shot exemplar prompts and no…

Computation and Language · Computer Science 2024-12-11 Arda Sevinc , Abdurrahman Gumus

Chain-of-thought (CoT), tree-of-thought (ToT), and related techniques work surprisingly well in practice for some complex reasoning tasks with Large Language Models (LLMs), but why? This work seeks the underlying reasons by conducting…

Artificial Intelligence · Computer Science 2024-06-19 Liwei Kang , Zirui Zhao , David Hsu , Wee Sun Lee

In the field of chemical engineering, traditional data-processing and prediction methods face significant challenges. Machine-learning and large-language models (LLMs) also have their respective limitations. This paper explores the…

Machine Learning · Computer Science 2025-02-19 Tianhang Zhou , Yingchun Niu , Xingying Lan , Chunming Xu