English
Related papers

Related papers: Enhancing Generalization in Chain of Thought Reaso…

200 papers

Eliciting "chain of thought" (CoT) rationales -- sequences of token that convey a "reasoning" process -- has been shown to consistently improve LLM performance on tasks like question answering. More recent efforts have shown that such…

Computation and Language · Computer Science 2024-10-01 Somin Wadhwa , Silvio Amir , Byron C. Wallace

Large language models (LLMs) are often constrained by rigid reasoning processes, limiting their ability to generate creative and diverse responses. To address this, a novel framework called LADDER is proposed, combining Chain-of-Thought…

Computation and Language · Computer Science 2025-06-17 Xintong Tang , Meiru Zhang , Shang Xiao , Junzhao Jin , Zihan Zhao , Liwei Li , Yang Zheng , Bangyi Wu

Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller…

Computation and Language · Computer Science 2023-11-08 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Hongbo Zhang , Sung Ju Hwang , Alexander Min

How to usefully encode compositional task structure has long been a core challenge in AI. Recent work in chain of thought prompting has shown that for very large neural language models (LMs), explicitly demonstrating the inferential steps…

Computation and Language · Computer Science 2022-10-25 Victor S. Bursztyn , David Demeter , Doug Downey , Larry Birnbaum

Pretrained large language models (LLMs) are increasingly utilized across a wide range of natural language processing (NLP) tasks due to their impressive capabilities as few-shot learners. Recent techniques, such as chain-of-thought (CoT)…

Machine Learning · Computer Science 2024-12-02 Kamesh R

Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks by generating intermediate reasoning steps. However, most existing approaches focus on hard token decoding, which constrains reasoning…

Computation and Language · Computer Science 2025-05-28 Yige Xu , Xu Guo , Zhiwei Zeng , Chunyan Miao

There has been a growing interest in enhancing the mathematical problem-solving (MPS) capabilities of large language models. While the majority of research efforts concentrate on creating specialized models to solve mathematical problems,…

Computation and Language · Computer Science 2025-07-08 Ruochen Zhou , Minrui Xu , Shiqi Chen , Junteng Liu , Yunqi Li , Xinxin Lin , Zhengyu Chen , Junxian He

Integrating reasoning in large language models and large vision-language models has recently led to significant improvement of their capabilities. However, the generalization of reasoning models is still vaguely defined and poorly…

Machine Learning · Computer Science 2026-02-18 Yannic Neuhaus , Nicolas Flammarion , Matthias Hein , Francesco Croce

Chain-of-thought (CoT) prompting improves LLM reasoning but incurs high latency and memory cost due to verbose traces, motivating CoT compression with preserved correctness. Existing methods either shorten CoTs at the semantic level, which…

Artificial Intelligence · Computer Science 2026-01-29 Zhenxuan Fan , Jie Cao , Yang Dai , Zheqi Lv , Wenqiao Zhang , Zhongle Xie , Peng LU , Beng Chin Ooi

Recent advances in reasoning-focused Large Language Models (LLMs) have introduced Chain-of-Thought (CoT) traces - intermediate reasoning steps generated before a final answer. These traces, as in DeepSeek R1, guide inference and train…

Computation and Language · Computer Science 2026-04-20 Siddhant Bhambri , Upasana Biswas , Subbarao Kambhampati

Chain-of-Though (CoT) represents a common strategy for reasoning in Large Language Models (LLMs) by decomposing complex tasks into intermediate inference steps. However, explanations generated via CoT are susceptible to content biases that…

Computation and Language · Computer Science 2026-03-31 Leonardo Ranaldi , Marco Valentino , Andrè Freitas

The knowledge-augmented deep learning paradigm refers to a paradigm in which domain knowledge is identified and integrated into deep models. Conventional methods typically employ task-specific approaches to gather external knowledge from…

Computation and Language · Computer Science 2023-07-06 Dingjun Wu , Jing Zhang , Xinmei Huang

With the wide proliferation of Deep Neural Networks in high-stake applications, there is a growing demand for explainability behind their decision-making process. Concept learning models attempt to learn high-level 'concepts' - abstract…

Machine Learning · Computer Science 2024-05-07 Sanchit Sinha , Guangzhi Xiong , Aidong Zhang

Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating redundant…

Computation and Language · Computer Science 2026-04-15 Hongyuan Yuan , Xinran He , Run Shao , Bolei He , Xianwei Xue , Mengke Chen , Qiutong Pan , Haiwei Wang , Haifeng Li

Chain-of-thought (CoT) prompting is a simple and effective method for improving the reasoning capabilities of Large Language Models (LLMs). The basic idea of CoT is to let LLMs break down their thought processes step-by-step by putting…

Computation and Language · Computer Science 2025-06-16 Yoonjeong Park , Hyunjin Kim , Chanyeol Choi , Junseong Kim , Jy-yong Sohn

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual…

Machine Learning · Computer Science 2026-05-22 Rosie Zhao , Anshul Shah , Xiaoyu Zhu , Xinke Deng , Zhongyu Jiang , Yang Yang , Joerg Liebelt , Arnab Mondal

With the remarkable success of Multimodal Large Language Models (MLLMs) in perception tasks, enhancing their complex reasoning capabilities has emerged as a critical research focus. Existing models still suffer from challenges such as…

Computation and Language · Computer Science 2025-12-01 Wenxin Zhu , Andong Chen , Yuchen Song , Kehai Chen , Conghui Zhu , Ziyan Chen , Tiejun Zhao

The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of LLMs on complex reasoning tasks. Moreover, the significance…

Computation and Language · Computer Science 2024-03-05 Bingshuai Liu , Chenyang Lyu , Zijun Min , Zhanyu Wang , Jinsong Su , Longyue Wang

Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal…

Computation and Language · Computer Science 2024-04-03 Qihuang Zhong , Liang Ding , Juhua Liu , Bo Du , Dacheng Tao

Large language models (LLMs) have shown remarkable reasoning capabilities when trained with chain-of-thought (CoT) supervision. However, the long and verbose CoT traces, especially those distilled from large reasoning models (LRMs) such as…

Machine Learning · Computer Science 2025-06-05 Jinghan Jia , Hadi Reisizadeh , Chongyu Fan , Nathalie Baracaldo , Mingyi Hong , Sijia Liu