English
Related papers

Related papers: Why Does Self-Distillation (Sometimes) Degrade the…

200 papers

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while…

Machine Learning · Computer Science 2026-03-23 Siyan Zhao , Zhihui Xie , Mengchen Liu , Jing Huang , Guan Pang , Feiyu Chen , Aditya Grover

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Artificial Intelligence · Computer Science 2025-11-14 Yuetai Li , Xiang Yue , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Bill Yuchen Lin , Bhaskar Ramasubramanian , Radha Poovendran

Artificial Intelligence (AI) has increasingly influenced modern society, recently in particular through significant advancements in Large Language Models (LLMs). However, high computational and storage demands of LLMs still limit their…

Computation and Language · Computer Science 2025-04-23 Daniel Hendriks , Philipp Spitzer , Niklas Kühl , Gerhard Satzger

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

Recent studies have shown that reinforcement learning with verifiable rewards (RLVR) enhances overall accuracy (pass@1) but often fails to improve capability (pass@k) of LLMs in reasoning tasks, while distillation can improve both. In this…

Artificial Intelligence · Computer Science 2025-11-03 Minwu Kim , Anubhav Shrestha , Safal Shrestha , Aadim Nepal , Keith Ross

On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level…

Machine Learning · Computer Science 2026-05-22 Hongbin Zhang , Chaozheng Wang , Kehai Chen , Youcheng Pan , Yang Xiang , Jinpeng Wang , Min Zhang

We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite the performance gains of OPSD, we identify a…

Machine Learning · Computer Science 2026-05-13 Yuxiao Yang , Xiaoyun Wang , Weitong Zhang

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Machine Learning · Computer Science 2026-05-12 Khouloud Saadi , Di Wang

Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…

Computation and Language · Computer Science 2026-05-15 Yumeng Zhang , Zhengbang Yang , Yevin Nikhel Goonatilake , Zhuangdi Zhu

On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervision. Existing objectives typically weight the teacher's…

Artificial Intelligence · Computer Science 2026-05-14 Junlong Ke , Zichen Wen , Weijia Li , Conghui He , Linfeng Zhang

Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex tasks. While revealing these reasoning traces helps users better follow, verify, and learn from…

Computation and Language · Computer Science 2025-10-14 Jiayu Ding , Lei Cui , Li Dong , Nanning Zheng , Furu Wei

Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools? We study this setting starting only from unlabeled seed questions with no ground-truth…

Computation and Language · Computer Science 2026-05-27 Tony Lee , Percy Liang

On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution. A design choice shared by nearly all such methods,…

Artificial Intelligence · Computer Science 2026-05-28 Zihao Han , Tiangang Zhang , Huaibin Wang , Yilun Sun

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

Computation and Language · Computer Science 2026-03-17 Minsang Kim , Seung Jun Baek

Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…

Information Retrieval · Computer Science 2026-05-15 Danyang Liu , Kan Li

The recent trend towards utilisation of reasoning models has improved the performance of Large Language Models (LLMs) across many tasks which involve logical steps. One linguistic task that could benefit from this framing is idiomaticity…

Computation and Language · Computer Science 2025-08-20 Dylan Phelps , Rodrigo Wilkens , Edward Gow-Smith , Thomas Pickard , Maggie Mi , Aline Villavicencio

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same…

Artificial Intelligence · Computer Science 2026-05-12 Han Yang , Mingyan Wu , Bailan He , Zeyu Cao , Sikuan Yan , Kevin Qinghong Lin , Zifeng Ding

As large language models (LLMs) are increasingly used for factual question-answering, it becomes more important for LLMs to have the capability to communicate the likelihood that their answer is correct. For these verbalized expressions of…

Computation and Language · Computer Science 2025-12-15 Sophia Hager , David Mueller , Kevin Duh , Nicholas Andrews

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

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
‹ Prev 1 2 3 10 Next ›