English
Related papers

Related papers: DRP: Distilled Reasoning Pruning with Skill-aware …

200 papers

The high inference cost of Large Language Models (LLMs) poses challenges, especially for tasks requiring lengthy outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed…

Computation and Language · Computer Science 2025-11-25 Alfredo Garrachón Ruiz , Tomás de la Rosa , Daniel Borrajo

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work…

This work introduces a novel approach to pruning deep learning models by using distilled data. Unlike conventional strategies which primarily focus on architectural or algorithmic optimization, our method reconsiders the role of data in…

Machine Learning · Computer Science 2023-08-10 Luke McDermott , Daniel Cummings

Chain-of-thought (CoT) reasoning in large language models (LLMs) can be formalized as a latent variable problem, where the model needs to generate intermediate reasoning steps. While prior approaches such as iterative reward-ranked…

Machine Learning · Computer Science 2025-05-06 Jiarui Yao , Yifan Hao , Hanning Zhang , Hanze Dong , Wei Xiong , Nan Jiang , Tong Zhang

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun

Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR…

Computation and Language · Computer Science 2022-11-07 Harsh Trivedi , Niranjan Balasubramanian , Tushar Khot , Ashish Sabharwal

Large Reasoning Models (LRMs) have shown impressive capabilities in complex problem-solving, often benefiting from training on difficult mathematical problems that stimulate intricate reasoning. Recent efforts have explored automated…

Machine Learning · Computer Science 2025-09-26 Qizhi Pei , Zhuoshi Pan , Honglin Lin , Xin Gao , Yu Li , Zinan Tang , Conghui He , Rui Yan , Lijun Wu

Large language model (LLM)-based recommender models that bridge users and items through textual prompts for effective semantic reasoning have gained considerable attention. However, few methods consider the underlying rationales behind…

Computation and Language · Computer Science 2025-01-09 Xinfeng Wang , Jin Cui , Yoshimi Suzuki , Fumiyo Fukumoto

Recently, the demand for small and efficient reasoning models to support real-world applications has driven the development of knowledge distillation techniques that balance reasoning performance and inference speed. In this paper, we…

Computation and Language · Computer Science 2025-11-04 Wenrui Cai , Chengyu Wang , Junbing Yan , Jun Huang , Xiangzhong Fang

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…

Computation and Language · Computer Science 2024-06-13 Ehsan Latif , Luyang Fang , Ping Ma , Xiaoming Zhai

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length,…

Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as…

Machine Learning · Computer Science 2026-05-07 Akiyoshi Tomihari , Issei Sato

Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding. However, realizing this potential in practice remains challenging: reducing the number of…

Chain-of-Thought (CoT) distillation from Large Language Models (LLMs) often induces "overthinking" in Small Language Models (SLMs), leading to performance degradation and excessive token consumption. In this study, we propose Disciplined…

Computation and Language · Computer Science 2026-02-26 Shunsuke Ubukata

Large Language Models (LLMs) have shown remarkable reasoning capabilities, while their practical applications are limited by severe factual hallucinations due to limitations in the timeliness, accuracy, and comprehensiveness of their…

Artificial Intelligence · Computer Science 2025-06-10 Xinyan Guan , Jiali Zeng , Fandong Meng , Chunlei Xin , Yaojie Lu , Hongyu Lin , Xianpei Han , Le Sun , Jie Zhou

Language models (LMs) have yielded impressive results on many language reasoning tasks, but their unexpected errors raise doubts about their reasoning abilities. In light of this, there is growing interest in finetuning/prompting LMs with…

Computation and Language · Computer Science 2023-05-23 Aaron Chan , Zhiyuan Zeng , Wyatt Lake , Brihi Joshi , Hanjie Chen , Xiang Ren

Distilling explicit chain-of-thought reasoning paths has emerged as an effective method for improving the reasoning abilities of large language models (LLMs) across various tasks. However, when tackling complex tasks that pose significant…

Computation and Language · Computer Science 2024-04-15 Jierui Li , Raymond Mooney

Chain-of-thought reasoning, while powerful, can produce unnecessarily verbose output for simpler problems. We present a framework for difficulty-aware reasoning that teaches models to dynamically adjust reasoning depth based on problem…

Computation and Language · Computer Science 2025-09-08 Abdul Waheed , Chancharik Mitra , Laurie Z. Wang , Deva Ramanan , Bhiksha Raj

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Alaa Asfour , Christopher Indris , Leihan Chen , Tejas Vyas , Guanghui Wang

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…

Computation and Language · Computer Science 2024-06-11 Xin Chen , Hanxian Huang , Yanjun Gao , Yi Wang , Jishen Zhao , Ke Ding
‹ Prev 1 8 9 10 Next ›