English
Related papers

Related papers: Internalizing Curriculum Judgment for LLM Reinforc…

200 papers

Reinforcement Learning with Verifiable Rewards~(RLVR) has emerged as a powerful learn-to-reason paradigm for large reasoning models to tackle complex tasks. However, the current RLVR paradigm is still not efficient enough, as it works in a…

Computation and Language · Computer Science 2026-03-10 Junjie Zhang , Guozheng Ma , Shunyu Liu , Haoyu Wang , Jiaxing Huang , Ting-En Lin , Fei Huang , Yongbin Li , Dacheng Tao

The rapid advancement of large language models (LLMs) has opened new possibilities for their adoption as evaluative judges. This paper introduces Themis, a fine-tuned LLM judge that delivers sophisticated context-aware evaluations. We…

Computation and Language · Computer Science 2025-02-06 Renjun Hu , Yi Cheng , Libin Meng , Jiaxin Xia , Yi Zong , Xing Shi , Wei Lin

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Machine Learning · Computer Science 2026-01-22 Song Lai , Haohan Zhao , Rong Feng , Changyi Ma , Wenzhuo Liu , Hongbo Zhao , Xi Lin , Dong Yi , Qingfu Zhang , Hongbin Liu , Gaofeng Meng , Fei Zhu

Recent advances in reinforcement learning with verifiable, rule-based rewards have greatly enhanced the reasoning capabilities and out-of-distribution generalization of VLMs/LLMs, obviating the need for manually crafted reasoning chains.…

Artificial Intelligence · Computer Science 2025-05-27 Shaohao Rui , Kaitao Chen , Weijie Ma , Xiaosong Wang

Large language models (LLMs) acquire extensive prior knowledge through large-scale pretraining and can be further enhanced via supervised fine-tuning (SFT) or reinforcement learning (RL)-based post-training. A growing body of evidence has…

Machine Learning · Computer Science 2026-01-28 Honglin Zhang , Qianyue Hao , Fengli Xu , Yong Li

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…

Machine Learning · Computer Science 2023-05-29 Cevahir Koprulu , Ufuk Topcu

Scaling test-time computation, or affording a generator large language model (LLM) extra compute during inference, typically employs the help of external non-generative evaluators (i.e., reward models). Concurrently, LLM-judges, models…

Computation and Language · Computer Science 2025-05-23 Yilun Zhou , Austin Xu , Peifeng Wang , Caiming Xiong , Shafiq Joty

Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands. However, the progress is hampered by the lack of benchmarks with rigorous,…

Computation and Language · Computer Science 2026-02-16 Haiyun Guo , Zhiyan Hou , Yandu Sun , Jinghan He , Yu Chen , Yuzhe Zhou , Yuheng Jia , Jinqiao Wang , Tat-Seng Chua

The process of meta-learning algorithms from data, instead of relying on manual design, is growing in popularity as a paradigm for improving the performance of machine learning systems. Meta-learning shows particular promise for…

Machine Learning · Computer Science 2025-09-11 Alexander David Goldie , Zilin Wang , Jaron Cohen , Jakob Nicolaus Foerster , Shimon Whiteson

Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and the learning of additional world knowledge. However, the…

Computation and Language · Computer Science 2024-08-13 Mengjie Ren , Boxi Cao , Hongyu Lin , Cao Liu , Xianpei Han , Ke Zeng , Guanglu Wan , Xunliang Cai , Le Sun

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

Machine Learning · Computer Science 2025-11-25 Maxime Heuillet , Yufei Cui , Boxing Chen , Audrey Durand , Prasanna Parthasarathi

Robust reinforcement learning methods typically focus on suppressing unreliable experiences or corrupted rewards, but they lack the ability to reason about the reliability of their own learning process. As a result, such methods often…

Machine Learning · Computer Science 2026-03-24 Zhipeng Zhang , Xiongfei Su , Kai Li

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in language reasoning, its application to autoregressive Text-to-Image (T2I) generation is often constrained by the limited availability of human preference data. This…

Artificial Intelligence · Computer Science 2026-02-02 Yihang Chen , Yuanhao Ban , Yunqi Hong , Cho-Jui Hsieh

Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable…

Machine Learning · Computer Science 2025-06-26 Yanzhi Zhang , Zhaoxi Zhang , Haoxiang Guan , Yilin Cheng , Yitong Duan , Chen Wang , Yue Wang , Shuxin Zheng , Jiyan He

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Large language models (LLMs) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced with spurious prompt-level cues such as consensus claims or…

Computers and Society · Computer Science 2026-04-07 Qian Wang , Xuandong Zhao , Zirui Zhang , Zhanzhi Lou , Nuo Chen , Dawn Song , Bingsheng He

The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provided only at the end of a sequence into fine-grained learning…

Machine Learning · Computer Science 2026-05-26 Fei Ding , Yongkang Zhang , Runhao Liu , Yuhao Liao , Zijian Zeng , Sibo wang , Huiming Yang

Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model…

Computation and Language · Computer Science 2024-09-16 Ziqi Wang , Le Hou , Tianjian Lu , Yuexin Wu , Yunxuan Li , Hongkun Yu , Heng Ji

The competitive performance of neural machine translation (NMT) critically relies on large amounts of training data. However, acquiring high-quality translation pairs requires expert knowledge and is costly. Therefore, how to best utilize a…

Computation and Language · Computer Science 2020-04-14 Mingjun Zhao , Haijiang Wu , Di Niu , Xiaoli Wang

In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…

Information Retrieval · Computer Science 2025-09-22 Haowei Liu , Xuyang Wu , Guohao Sun , Zhiqiang Tao , Yi Fang