English
Related papers

Related papers: BOW: Reinforcement Learning for Bottlenecked Next …

200 papers

Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Prior work introduces supervision on intermediate steps but…

Computation and Language · Computer Science 2026-01-30 Jundong Xu , Hao Fei , Huichi Zhou , Xin Quan , Qijun Huang , Shengqiong Wu , William Yang Wang , Mong-Li Lee , Wynne Hsu

Recent advances in diffusion language models (DLMs) have presented a promising alternative to traditional autoregressive large language models (LLMs). However, DLMs still lag behind LLMs in reasoning performance, especially as the number of…

Computation and Language · Computer Science 2025-10-27 Chenglong Wang , Yang Gan , Hang Zhou , Chi Hu , Yongyu Mu , Kai Song , Murun Yang , Bei Li , Chunliang Zhang , Tongran Liu , Jingbo Zhu , Zhengtao Yu , Tong Xiao

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models (LLMs). In this context, models explore reasoning trajectories and exploit rollouts…

Machine Learning · Computer Science 2026-03-02 Yuyang Ding , Chi Zhang , Juntao Li , Haibin Lin , Min Zhang

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks by effectively utilizing a prompting strategy. However, they are highly sensitive to input perturbations, such as typographical errors or slight…

Computation and Language · Computer Science 2026-05-27 Lin Mu , Guowei Chu , Li Ni , Lei Sang , Yiwen Zhang

Recent studies, including DeepSeek-R1 and Kimi-k1.5, have demonstrated that reinforcement learning with rule-based, binary-valued reward functions can significantly enhance the reasoning capabilities of large language models. These models…

Machine Learning · Computer Science 2025-06-04 Changyi Xiao , Mengdi Zhang , Yixin Cao

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Machine Learning · Computer Science 2025-05-22 Tong Wu , Chong Xiang , Jiachen T. Wang , G. Edward Suh , Prateek Mittal

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

Artificial Intelligence · Computer Science 2025-07-08 Saksham Sahai Srivastava , Vaneet Aggarwal

Process Reward Models (PRMs) emerge as a promising approach for process supervision in mathematical reasoning of Large Language Models (LLMs), which aim to identify and mitigate intermediate errors in the reasoning processes. However, the…

Computation and Language · Computer Science 2025-06-06 Zhenru Zhang , Chujie Zheng , Yangzhen Wu , Beichen Zhang , Runji Lin , Bowen Yu , Dayiheng Liu , Jingren Zhou , Junyang Lin

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow…

Machine Learning · Computer Science 2025-09-30 Haoran He , Yuxiao Ye , Qingpeng Cai , Chen Hu , Binxing Jiao , Daxin Jiang , Ling Pan

The emergence of discourse-like tokens such as "wait" and "therefore" in large language models (LLMs) has offered a unique window into their reasoning processes. However, systematic analyses of how such signals vary across training…

Computation and Language · Computer Science 2026-01-27 Jaehui Hwang , Dongyoon Han , Sangdoo Yun , Byeongho Heo

Designing predictive models for subjective problems in natural language processing (NLP) remains challenging. This is mainly due to its non-deterministic nature and different perceptions of the content by different humans. It may be solved…

Artificial Intelligence · Computer Science 2023-12-12 Piotr Miłkowski , Konrad Karanowski , Patryk Wielopolski , Jan Kocoń , Przemysław Kazienko , Maciej Zięba

High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended forecasting questions. To scale up training data, we synthesize novel forecasting…

Machine Learning · Computer Science 2026-01-06 Nikhil Chandak , Shashwat Goel , Ameya Prabhu , Moritz Hardt , Jonas Geiping

The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss functions and leveraging human feedback, are being adopted…

Computation and Language · Computer Science 2025-01-20 Suvodip Dey , Maunendra Sankar Desarkar

Modern language models mostly take sub-words as input, a design that balances the trade-off between vocabulary size, number of parameters, and performance. However, sub-word tokenization still has disadvantages like not being robust to…

Computation and Language · Computer Science 2022-11-24 Chu-Tak Lee , Qipeng Guo , Xipeng Qiu

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under drifting non-stationarity, i.e., both the reward and state transition distributions are allowed to evolve over time, as long as their respective…

Machine Learning · Computer Science 2020-06-26 Wang Chi Cheung , David Simchi-Levi , Ruihao Zhu

Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training…

Despite the remarkable capabilities of large language models (LLMs) across a range of tasks, mathematical reasoning remains a challenging frontier. Motivated by the observation that humans learn more effectively when prompted not what to…

Computation and Language · Computer Science 2025-08-08 Maria-Eleni Zoumpoulidi , Georgios Paraskevopoulos , Alexandros Potamianos

Best-of-N (BoN) is a popular and effective algorithm for aligning language models to human preferences. The algorithm works as follows: at inference time, N samples are drawn from the language model, and the sample with the highest reward,…

Computation and Language · Computer Science 2025-03-05 Afra Amini , Tim Vieira , Elliott Ash , Ryan Cotterell

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Computation and Language · Computer Science 2025-04-18 Liyi Zhang , Veniamin Veselovsky , R. Thomas McCoy , Thomas L. Griffiths

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…

Neural and Evolutionary Computing · Computer Science 2025-05-26 Rishi Hazra , Alkis Sygkounas , Andreas Persson , Amy Loutfi , Pedro Zuidberg Dos Martires