English
Related papers

Related papers: KNIFE: Distilling Reasoning Knowledge From Free-Te…

200 papers

Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has not been a systematic…

Computation and Language · Computer Science 2025-07-03 Yang Li , Youssef Emad , Karthik Padthe , Jack Lanchantin , Weizhe Yuan , Thao Nguyen , Jason Weston , Shang-Wen Li , Dong Wang , Ilia Kulikov , Xian Li

Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences. However, it carries the…

Computation and Language · Computer Science 2024-04-30 Tingfeng Hui , Zhenyu Zhang , Shuohuan Wang , Weiran Xu , Yu Sun , Hua Wu

Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away from the supervised fine-tuning (SFT) paradigm. Many studies…

Knowledge distillation (KD) is widely used to train small, high-performing student language models (LMs) using large teacher LMs. While effective in fine-tuning, KD during pre-training faces efficiency, flexibility, and effectiveness…

Computation and Language · Computer Science 2025-03-20 Yuxian Gu , Hao Zhou , Fandong Meng , Jie Zhou , Minlie Huang

Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP), owing to their excellent understanding and generation abilities. Remarkably, what further sets these models apart is the massive…

Computation and Language · Computer Science 2022-11-10 Daliang Li , Ankit Singh Rawat , Manzil Zaheer , Xin Wang , Michal Lukasik , Andreas Veit , Felix Yu , Sanjiv Kumar

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Computation and Language · Computer Science 2025-10-21 Qingcheng Zeng , Weihao Xuan , Leyang Cui , Rob Voigt

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

Computation and Language · Computer Science 2025-10-29 ChangSu Choi , Hoyun Song , Dongyeon Kim , WooHyeon Jung , Minkyung Cho , Sunjin Park , NohHyeob Bae , Seona Yu , KyungTae Lim

Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and…

Artificial Intelligence · Computer Science 2026-04-28 Guangxiang Zhao , Qilong Shi , Xusen Xiao , Xiangzheng Zhang , Tong Yang , Lin Sun

Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs…

Computation and Language · Computer Science 2024-08-12 Khai Loong Aw , Syrielle Montariol , Badr AlKhamissi , Martin Schrimpf , Antoine Bosselut

Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL). However, despite these successes, RL in its current form…

Artificial Intelligence · Computer Science 2026-03-12 Lu Ma , Hao Liang , Meiyi Qiang , Lexiang Tang , Xiaochen Ma , Zhen Hao Wong , Junbo Niu , Chengyu Shen , Runming He , Yanhao Li , Bin Cui , Wentao Zhang

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align…

Computation and Language · Computer Science 2025-06-04 Ziyin Zhang , Jiahao Xu , Zhiwei He , Tian Liang , Qiuzhi Liu , Yansi Li , Linfeng Song , Zhenwen Liang , Zhuosheng Zhang , Rui Wang , Zhaopeng Tu , Haitao Mi , Dong Yu

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…

Computation and Language · Computer Science 2025-11-14 Mingye Zhu , Yi Liu , Zheren Fu , Quan Wang , Yongdong Zhang

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Machine Learning · Computer Science 2026-02-10 Zahra Rahimi Afzal , Tara Esmaeilbeig , Mojtaba Soltanalian , Mesrob I. Ohannessian

Tools are essential for large language models (LLMs) to acquire up-to-date information and take consequential actions in external environments. Existing work on tool-augmented LLMs primarily focuses on the broad coverage of tools and the…

Computation and Language · Computer Science 2024-03-08 Boshi Wang , Hao Fang , Jason Eisner , Benjamin Van Durme , Yu Su

To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural language to reason…

Computation and Language · Computer Science 2023-11-03 Yuntian Deng , Kiran Prasad , Roland Fernandez , Paul Smolensky , Vishrav Chaudhary , Stuart Shieber

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Qirui Jiao , Daoyuan Chen , Yilun Huang , Yaliang Li , Ying Shen

We study how reasoning evolves in a language model -- from supervised fine-tuning (SFT) to reinforcement learning (RL) -- by analyzing how a set of theoretically-inspired datasets influences language model performance in chess. We find that…

Machine Learning · Computer Science 2026-05-05 Lucas Dionisopoulos , Nicklas Majamaki , Prithviraj Ammanabrolu

Reasoning in mathematical domains remains a significant challenge for relatively small language models (LMs). Many current methods focus on specializing LMs in mathematical reasoning and rely heavily on knowledge distillation from powerful…

Artificial Intelligence · Computer Science 2023-07-18 Zhenwen Liang , Dian Yu , Xiaoman Pan , Wenlin Yao , Qingkai Zeng , Xiangliang Zhang , Dong Yu

Inductive reasoning is an essential capability for large language models (LLMs) to achieve higher intelligence, which requires the model to generalize rules from observed facts and then apply them to unseen examples. We present MIRAGE, a…

Computation and Language · Computer Science 2025-03-03 Jiachun Li , Pengfei Cao , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao