English
Related papers

Related papers: Improving In-Context Learning with Reasoning Disti…

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

Recent reasoning LLMs (RLMs), especially those trained with verifier-based reinforcement learning, often perform worse with few-shot CoT than with direct answering. We revisit this paradox using high-quality reasoning traces from…

Computation and Language · Computer Science 2025-09-30 Haonan Wang , Weida Liang , Zihang Fu , Nie Zheng , Yifan Zhang , Yao Tong , Tongyao Zhu , Hao Jiang , Chuang Li , Jiaying Wu , Kenji Kawaguchi

Reasoning models think out loud, but much of what they say is noise. We introduce CRISP (Compressed Reasoning via Iterative Self-Policy Distillation), a method that teaches models to reason more concisely by distilling their own concise…

Machine Learning · Computer Science 2026-04-14 Hejian Sang , Yuanda Xu , Zhengze Zhou , Ran He , Zhipeng Wang , Jiachen Sun

Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…

Computation and Language · Computer Science 2025-10-14 Zhichao Xu , Minheng Wang , Yawei Wang , Wenqian Ye , Yuntao Du , Yunpu Ma , Yijun Tian

Multi-agent interactions between Large Language Model (LLM) agents have shown major improvements on diverse reasoning tasks. However, these involve long generations from multiple models across several rounds, making them expensive.…

Computation and Language · Computer Science 2024-06-11 Justin Chih-Yao Chen , Swarnadeep Saha , Elias Stengel-Eskin , Mohit Bansal

Large language models (LLMs) have gained extended context windows through scaling positional encodings and lightweight continual pre-training. However, this often leads to degraded performance on short-text tasks, while the reasons for this…

Computation and Language · Computer Science 2025-05-29 Zican Dong , Junyi Li , Jinhao Jiang , Mingyu Xu , Wayne Xin Zhao , Bingning Wang , Weipeng Chen

Large Language Models (LLMs) demonstrate proficiency across diverse tasks but often require targeted adaptations for specific applications. Various methods have been proposed to facilitate this adaptation, including fewshot fine-tuning,…

Machine Learning · Computer Science 2025-11-10 Rajesh Upadhayaya , Manish Raj Osti , Zachary Smith , Chritopher Kottmyer

On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, existing OPSD methods often yield limited gains on in-domain…

Computation and Language · Computer Science 2026-05-28 Ziqi Zhao , Xinyu Ma , Liu Yang , Yujie Feng , Daiting Shi , Jingzhou He , Xin Xin , Zhaochun Ren , Xiao-Ming Wu

Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving. Recent methods have improved reasoning through expanded corpus and multistage training…

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts…

Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student model against two objectives: a task-specific objective (e.g.,…

Computation and Language · Computer Science 2022-06-07 Zhengxuan Wu , Atticus Geiger , Josh Rozner , Elisa Kreiss , Hanson Lu , Thomas Icard , Christopher Potts , Noah D. Goodman

Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. The standard alternative, fine-tuning smaller models, often sacrifices…

Computation and Language · Computer Science 2026-02-25 Sanket Badhe , Deep Shah

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

As the field continues its push for ever more resources, this work turns the spotlight on a critical question: how can vision-language models (VLMs) be adapted to thrive in low-resource, budget-constrained settings? While large VLMs offer…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Zhiqi Kang , Rahaf Aljundi , Vaggelis Dorovatas , Karteek Alahari

Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distillation, can be a cost-effective way to boost reasoning…

Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find that few-shot demonstrations can sometimes bring negative…

Computation and Language · Computer Science 2024-12-18 Jiayu Liu , Zhenya Huang , Chaokun Wang , Xunpeng Huang , Chengxiang Zhai , Enhong Chen

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models…

Machine Learning · Computer Science 2022-11-03 Cody Blakeney , Jessica Zosa Forde , Jonathan Frankle , Ziliang Zong , Matthew L. Leavitt

Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical…

Computation and Language · Computer Science 2025-09-03 Weihua Du , Pranjal Aggarwal , Sean Welleck , Yiming Yang

Large language models (LLMs) have achieved remarkable progress in mathematical reasoning, but this ability is not equally accessible across languages. Especially low-resource languages exhibit much lower reasoning performance. To address…

Computation and Language · Computer Science 2026-05-12 Yihong Liu , Raoyuan Zhao , Michael A. Hedderich , Hinrich Schütze

Large language models (LLMs) exhibit enhanced reasoning at larger scales, driving efforts to distill these capabilities into smaller models via teacher-student learning. Previous works simply fine-tune student models on teachers' generated…

Computation and Language · Computer Science 2024-05-31 Chengwei Dai , Kun Li , Wei Zhou , Songlin Hu