English
Related papers

Related papers: Structural Rationale Distillation via Reasoning Sp…

200 papers

The push to compress and impart the proficiency of Large Language Models (LLMs) into more deployable and efficient Small Language Models (SLMs) has benefited from improvements in knowledge distillation (KD) techniques. These techniques…

Artificial Intelligence · Computer Science 2025-07-02 Shreyansh Padarha

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

Machine Learning · Computer Science 2026-04-13 Zhaoyang Zhang , Shuli Jiang , Yantao Shen , Yuting Zhang , Dhananjay Ram , Shuo Yang , Zhuowen Tu , Wei Xia , Stefano Soatto

Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long…

Computation and Language · Computer Science 2025-06-19 Zhaoyang Wang , Jinqi Jiang , Tian Qiu , Hui Liu , Xianfeng Tang , Huaxiu Yao

Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yiqing Shen , Mathias Unberath

Recent studies have demonstrated that Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters. To tackle the challenge of poor reasoning in Small Language Models (SLMs),…

Computation and Language · Computer Science 2025-08-19 Xinhe Li , Jiajun Liu , Peng Wang

Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading…

Computation and Language · Computer Science 2026-05-21 Jeonghye Kim , Xufang Luo , Minbeom Kim , Sangmook Lee , Dohyung Kim , Jiwon Jeon , Dongsheng Li , Yuqing Yang

While long Chain-of-Thought (CoT) distillation effectively transfers reasoning capability to smaller language models, the reasoning process often remains redundant and computational budget uncontrollable, leading to inefficient resource…

Computation and Language · Computer Science 2025-12-29 Lujie Niu , Lei Shen , Yi Jiang , Caixia Yuan , Xiaojie Wang , Wenbo Su , Bo zheng

Chain-of-thought (CoT) distillation aims to enhance small language models' (SLMs) reasoning by transferring multi-step reasoning capability from the larger teacher models. However, existing work underestimates rationale quality, focusing…

Computation and Language · Computer Science 2025-09-30 Jianzhi Yan , Le Liu , Youcheng Pan , Shiwei Chen , Yang Xiang , Buzhou Tang

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in solving complex mathematical problems. Recent studies show that distilling long reasoning trajectories can effectively enhance the reasoning…

Computation and Language · Computer Science 2026-01-16 Zhenghao Liu , Zhuoyang Wu , Xinze Li , Yukun Yan , Shuo Wang , Zulong Chen , Yu Gu , Ge Yu , Maosong Sun

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning trajectories remain sparse in unconstrained sampling, and…

Artificial Intelligence · Computer Science 2026-03-03 Po-Nien Kung , Zhen Yang , Jeffrey Luo , Cheng-Fu Yang , Haikang Deng , Zi-Yi Dou , Yinfei Yang , Nanyun Peng , Zhe Gan , Kai-Wei Chang

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge distillation (KD) over lengthy sequences with prompt (P),…

Computation and Language · Computer Science 2026-01-09 Wei-Rui Chen , Vignesh Kothapalli , Ata Fatahibaarzi , Hejian Sang , Shao Tang , Qingquan Song , Zhipeng Wang , Muhammad Abdul-Mageed

Step-by-step reasoning approaches like chain of thought (CoT) have proved to be very effective in inducing reasoning capabilities in large language models. However, the success of the CoT approach is fundamentally tied to the model size,…

Machine Learning · Computer Science 2023-05-19 Kumar Shridhar , Alessandro Stolfo , Mrinmaya Sachan

We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human…

Information Retrieval · Computer Science 2025-07-01 Chris Samarinas , Hamed Zamani

Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…

Information Retrieval · Computer Science 2024-08-21 Yu Cui , Feng Liu , Pengbo Wang , Bohao Wang , Heng Tang , Yi Wan , Jun Wang , Jiawei Chen

Distilling Chain-of-Thought (CoT) reasoning from large language models into compact student models presents a fundamental challenge: teacher rationales are often too verbose for smaller models to faithfully reproduce. Existing approaches…

Machine Learning · Computer Science 2026-03-06 Bowen Yu , Maolin Wang , Sheng Zhang , Binhao Wang , Yi Wen , Jingtong Gao , Bowen Liu , Zimo Zhao , Wanyu Wang , Xiangyu Zhao

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

Computation and Language · Computer Science 2026-01-16 Lechen Zhang , Yunxiang Zhang , Wei Hu , Lu Wang

Reasoning is increasingly crucial for various tasks. While chain-of-thought prompting enables large language models to leverage reasoning effectively, harnessing the reasoning capabilities of Vision-Language Models (VLMs) remains…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Guande Wu , Huan Song , Yawei Wang , Qiaojing Yan , Yijun Tian , Lin Lee Cheong , Panpan Xu

Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation…

Computation and Language · Computer Science 2024-11-26 Yijun Tian , Yikun Han , Xiusi Chen , Wei Wang , Nitesh V. Chawla

Effective code generation with language models hinges on two critical factors: accurately understanding the intent of the prompt and generating code that applies algorithmic reasoning to produce correct solutions capable of passing diverse…

Artificial Intelligence · Computer Science 2025-10-21 Amir Jalilifard , Anderson de Rezende Rocha , Marcos Medeiros Raimundo