English
Related papers

Related papers: Same Evidence, Different Answers: Canonical-Contex…

200 papers

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods…

In-context learning (ICL), teaching a large language model (LLM) to perform a task with few-shot demonstrations rather than adjusting the model parameters, has emerged as a strong paradigm for using LLMs. While early studies primarily used…

Computation and Language · Computer Science 2023-05-24 Man Luo , Xin Xu , Zhuyun Dai , Panupong Pasupat , Mehran Kazemi , Chitta Baral , Vaiva Imbrasaite , Vincent Y Zhao

Knowledge distillation is central to LLM post-training, yet its design space remains poorly understood, especially alongside reinforcement learning (RL). We show that the prevailing paradigms, off-policy distillation and on-policy…

Machine Learning · Computer Science 2026-05-19 Anhao Zhao , Haoran Xin , Yingqi Fan , Junlong Tong , Wenjie Li , Xiaoyu Shen

In-Context Learning (ICL) in Large Language Models (LLM) has emerged as the dominant technique for performing natural language tasks, as it does not require updating the model parameters with gradient-based methods. ICL promises to "adapt"…

Computation and Language · Computer Science 2025-03-05 Georgios Chochlakis , Niyantha Maruthu Pandiyan , Kristina Lerman , Shrikanth Narayanan

Multi-turn interactions with large language models typically retain the assistant's own past responses in the conversation history. In this work, we revisit this design choice by asking whether large language models benefit from…

Computation and Language · Computer Science 2026-03-02 Jenny Y. Huang , Leshem Choshen , Ramon Astudillo , Tamara Broderick , Jacob Andreas

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Yang Chen , Shuai Fu , Yu Zhang

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale…

Computation and Language · Computer Science 2024-05-28 Kaituo Feng , Changsheng Li , Xiaolu Zhang , Jun Zhou , Ye Yuan , Guoren Wang

Aligning small language models (SLMs) with human values typically involves distilling preference knowledge from large language models (LLMs). However, existing distillation methods model preference knowledge in teacher LLMs by comparing…

Computation and Language · Computer Science 2025-02-21 Yanggan Gu , Junzhuo Li , Sirui Huang , Xin Zou , Zhenghua Li , Xuming Hu

Contrastive Language-Image Pre-training (CLIP) models excel in integrating semantic information between images and text through contrastive learning techniques. It has achieved remarkable performance in various multimodal tasks. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Yifan Chen , Xiaozhen Qiao , Zhe Sun , Xuelong Li

Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised…

Machine Learning · Computer Science 2026-05-27 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor W. Tsang , Yang You

Chain-of-thought prompting (e.g., "Let's think step-by-step") primes large language models to verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic performance gains, benefits appear to emerge only for…

Computation and Language · Computer Science 2024-04-17 Liunian Harold Li , Jack Hessel , Youngjae Yu , Xiang Ren , Kai-Wei Chang , Yejin Choi

Large Language Models (LLMs) demonstrate strong reasoning capabilities for many tasks, often by explicitly decomposing the task via Chain-of-Thought (CoT) reasoning. Recent work on LLM-based translation designs hand-crafted prompts to…

Computation and Language · Computer Science 2025-09-24 Di Wu , Seth Aycock , Christof Monz

Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations,…

Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Zhanxin Gao , Jun Cen , Xiaobin Chang

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan

Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level. However, they usually ignore the correlation between multiple instances, which is also valuable for knowledge…

Computer Vision and Pattern Recognition · Computer Science 2019-04-04 Baoyun Peng , Xiao Jin , Jiaheng Liu , Shunfeng Zhou , Yichao Wu , Yu Liu , Dongsheng Li , Zhaoning Zhang

We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information. After confirming that discrete prompts…

Computation and Language · Computer Science 2023-03-08 Nathanaël Carraz Rakotonirina , Roberto Dessì , Fabio Petroni , Sebastian Riedel , Marco Baroni

Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the traditional representation learning that is based…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Kaiyang Zhou , Jingkang Yang , Chen Change Loy , Ziwei Liu

Large Language Models prompting, such as using in-context demonstrations, is a mainstream technique for invoking LLMs to perform high-performance and solid complex reasoning (e.g., mathematical reasoning, commonsense reasoning), and has the…

Artificial Intelligence · Computer Science 2024-10-08 Zhicheng Yang , Yinya Huang , Jing Xiong , Liang Feng , Xiaodan Liang , Yiwei Wang , Jing Tang

While large language models (LLMs) have demonstrated exceptional performance in recent natural language processing (NLP) tasks, their deployment poses substantial challenges due to high computational and memory demands in real-world…

Computation and Language · Computer Science 2024-02-27 Chenglin Li , Qianglong Chen , Liangyue Li , Caiyu Wang , Yicheng Li , Zulong Chen , Yin Zhang
‹ Prev 1 8 9 10 Next ›