English
Related papers

Related papers: Extrapolative Weight Averaging Reveals Correctness…

200 papers

Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked. Standard GRPO-style training updates the model using only the current step, while full…

Machine Learning · Computer Science 2026-05-11 Ismam Nur Swapnil , Aranya Saha , Tanvir Ahmed Khan , Mohammad Ariful Haque , Ser-Nam Lim

Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward…

Machine Learning · Computer Science 2026-05-11 Lucas Monteiro Paes , Natalie Mackraz , Barry-John Theobald , Federico Danieli

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further align the network with the intended usage. Yet the…

Recent advances in reinforcement learning with verifiable rewards (RLVR) show that large language models enhance their reasoning abilities when trained with verifiable signals. However, due to reward sparsity, effectiveness depends heavily…

Computation and Language · Computer Science 2026-01-27 Sanghwan Bae , Jiwoo Hong , Min Young Lee , Hanbyul Kim , JeongYeon Nam , Donghyun Kwak

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for…

Computation and Language · Computer Science 2026-01-16 Zihan Lin , Xiaohan Wang , Hexiong Yang , Jiajun Chai , Jie Cao , Guojun Yin , Wei Lin , Ran He

Achieving fault-tolerance will require a strong relationship between the hardware and the protocols used. Different approaches will therefore naturally have tailored proof-of-principle experiments to benchmark progress. Nevertheless,…

Quantum Physics · Physics 2024-05-28 Milan Liepelt , Tommaso Peduzzi , James R. Wootton

This study investigates the effectiveness of reinforcement learning (RL) fine-tuning techniques on a compact language model (Qwen2.5-0.5B Base) for two challenging tasks: instruction following and mathematical reasoning. We compare…

Computation and Language · Computer Science 2025-07-29 Yifu Han , Geo Zhang

An important challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies to attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), which decomposes…

Machine Learning · Computer Science 2025-02-07 Willem Röpke , Mathieu Reymond , Patrick Mannion , Diederik M. Roijers , Ann Nowé , Roxana Rădulescu

Machine learning applications frequently come with multiple diverse objectives and constraints that can change over time. Accordingly, trained models can be tuned with sets of hyper-parameters that affect their predictive behavior (e.g.,…

Machine Learning · Computer Science 2022-10-17 Bracha Laufer-Goldshtein , Adam Fisch , Regina Barzilay , Tommi Jaakkola

Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model's…

Computation and Language · Computer Science 2025-06-02 Mingjie Liu , Shizhe Diao , Ximing Lu , Jian Hu , Xin Dong , Yejin Choi , Jan Kautz , Yi Dong

Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable way is one of the current fundamental challenges in machine…

Machine Learning · Computer Science 2025-02-10 Niccolò Grillo , Andrea Toccaceli , Joël Mathys , Benjamin Estermann , Stefania Fresca , Roger Wattenhofer

Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on…

Machine Learning · Computer Science 2025-10-08 Andreas Hochlehnert , Hardik Bhatnagar , Vishaal Udandarao , Samuel Albanie , Ameya Prabhu , Matthias Bethge

Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning…

Machine Learning · Computer Science 2026-05-06 Xin-Ye Li , Ren-Biao Liu , Yun-Ji Zhang , Hui Sun , Zheng Xie , Ming Li

Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important and compelling research problem. Motivated by the…

Machine Learning · Computer Science 2025-06-02 Chujie Zheng , Ziqi Wang , Heng Ji , Minlie Huang , Nanyun Peng

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than…

Artificial Intelligence · Computer Science 2025-10-03 Phuc Minh Nguyen , Chinh D. La , Duy M. H. Nguyen , Nitesh V. Chawla , Binh T. Nguyen , Khoa D. Doan

We study in this paper the function approximation error of multivariate linear extrapolation. The sharp error bound of linear interpolation already exists in the literature. However, linear extrapolation is used far more often in…

Optimization and Control · Mathematics 2026-05-20 Liyuan Cao , Zaiwen Wen , Ya-xiang Yuan

The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning. In this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on…

Machine Learning · Computer Science 2024-05-29 Zhanpeng Zhou , Zijun Chen , Yilan Chen , Bo Zhang , Junchi Yan

Iterative methods are commonly used approaches to solve large, sparse linear systems, which are fundamental operations for many modern scientific simulations. When the large-scale iterative methods are running with a large number of ranks…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-05-30 Dingwen Tao , Sheng Di , Xin Liang , Zizhong Chen , Franck Cappello

Reinforcement learning (RL) is often credited with improving language model reasoning and generalization at the expense of degrading memorized knowledge. We challenge this narrative by observing that RL-enhanced models consistently…

Computation and Language · Computer Science 2025-11-11 Renfei Zhang , Manasa Kaniselvan , Niloofar Mireshghallah

This paper explores the combination of neural network quantization and entropy coding for memory footprint minimization. Edge deployment of quantized models is hampered by the harsh Pareto frontier of the accuracy-to-bitwidth tradeoff,…

Machine Learning · Computer Science 2024-06-11 C. Metz , O. Bichler , A. Dupret