English
Related papers

Related papers: SPARD: Self-Paced Curriculum for RL Alignment via …

200 papers

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…

Computation and Language · Computer Science 2025-11-13 Yibai Liu , Shihang Wang , Zeming Liu , Zheming Song , Junzhe Wang , Jingjing Liu , Qingjie Liu , Yunhong Wang

Self-play fine-tuning has demonstrated promising abilities in adapting large language models (LLMs) to downstream tasks with limited real-world data. The basic principle is to iteratively refine the model with real samples and synthetic…

Machine Learning · Computer Science 2025-12-09 Yibo Wang , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang , Lijun Zhang

Self-evolving reasoning frameworks let LLMs improve their reasoning capabilities by iteratively generating and solving problems without external supervision, using verifiable rewards. Ideally, such systems are expected to explore a diverse…

Machine Learning · Computer Science 2026-03-17 Vaibhav Mishra

Human communication depends on implicit social signals where effectiveness is shaped by tone, context, and conversational norms rather than semantic content alone. We introduce KARMA (Karma-Aligned Reward Model Adaptation), a framework for…

Computation and Language · Computer Science 2026-05-27 Jared Scott , Jesse Roberts

Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems. However, training these systems remains notoriously difficult due to the…

Artificial Intelligence · Computer Science 2026-02-10 Yanming Li , Xuelin Zhang , WenJie Lu , Ziye Tang , Maodong Wu , Haotian Luo , Tongtong Wu , Zijie Peng , Hongze Mi , Yibo Feng , Naiqiang Tan , Chao Huang , Hong Chen , Li Shen

Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human preference datasets but incur significant training costs and…

Computation and Language · Computer Science 2025-07-16 Yuancheng Xu , Udari Madhushani Sehwag , Alec Koppel , Sicheng Zhu , Bang An , Furong Huang , Sumitra Ganesh

Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement…

Machine Learning · Computer Science 2025-04-22 Cheng Qian , Emre Can Acikgoz , Qi He , Hongru Wang , Xiusi Chen , Dilek Hakkani-Tür , Gokhan Tur , Heng Ji

Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., a user) to self-improve, creating a self-loop system of training. However, existing works are limited in…

Machine Learning · Computer Science 2026-05-11 Seohyun Lee , Wenzhi Fang , Dong-Jun Han , Seyyedali Hosseinalipour , Christopher G. Brinton

Reliable evaluation of large language models is essential to ensure their applicability in practical scenarios. Traditional benchmark-based evaluation methods often rely on fixed reference answers, limiting their ability to capture…

Computation and Language · Computer Science 2025-10-02 Sujeong Lee , Hayoung Lee , Seongsoo Heo , Wonik Choi

Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through…

Computation and Language · Computer Science 2023-12-29 Yang Xu , Yongqiang Yao , Yufan Huang , Mengnan Qi , Maoquan Wang , Bin Gu , Neel Sundaresan

While large language models have made significant progress in mathematical reasoning, they remain unreliable at judging the correctness of their own solutions. Existing approaches that equip models with self-verification typically treat…

Computation and Language · Computer Science 2026-05-28 Haihui Pan , Junwei Bao , Hongfei Jiang , Yang Song

Aligning large language models (LLMs) with human preferences is essential for their applications. Recently, decoding-time alignment has emerged as an effective plug-and-play technique that avoids fine-tuning model parameters. This approach…

Computation and Language · Computer Science 2025-08-05 Bolian Li , Yifan Wang , Anamika Lochab , Ananth Grama , Ruqi Zhang

Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to open-domain…

Machine Learning · Computer Science 2026-04-14 Yang Zhao , Hepeng Wang , Xiao Ding , Yangou Ouyang , Bibo Cai , Kai Xiong , Jinglong Gao , Zhouhao Sun , Li Du , Bing Qin , Ting Liu

Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (LLMs), which frequently produce chains of thought (CoTs) containing errors even when the…

Computation and Language · Computer Science 2026-04-21 Raffaele Pisano , Roberto Navigli

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Jiahao Wang , Weiye Xu , Aijun Yang , Wengang Zhou , Lewei Lu , Houqiang Li , Xiaohua Wang , Jinguo Zhu

Large language models (LLMs) are at the forefront of transforming numerous domains globally. However, their inclusivity and effectiveness remain limited for non-Latin scripts and low-resource languages. This paper tackles the imperative…

Computation and Language · Computer Science 2025-01-08 Somnath Kumar , Vaibhav Balloli , Mercy Ranjit , Kabir Ahuja , Tanuja Ganu , Sunayana Sitaram , Kalika Bali , Akshay Nambi

Reward design is central to reinforcement learning from human feedback (RLHF) and alignment research. In this work, we propose a unified framework to study hard, continuous, and hybrid reward structures for fine-tuning large language models…

Machine Learning · Computer Science 2025-11-18 Subramanyam Sahoo

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Computation and Language · Computer Science 2025-05-27 Jinyan Su , Claire Cardie

This paper introduces SOLID (Synergizing Optimization and Large Language Models for Intelligent Decision-Making), a novel framework that integrates mathematical optimization with the contextual capabilities of large language models (LLMs).…

Artificial Intelligence · Computer Science 2025-11-20 Yinsheng Wang , Tario G You , Léonard Boussioux , Shan Liu

Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised adaptation (UA) for fine-grained classification with VLMs…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Eman Ali , Sathira Silva , Chetan Arora , Muhammad Haris Khan