English
Related papers

Related papers: What should post-training optimize? A test-time sc…

200 papers

Tree search has recently emerged as a powerful framework for aligning generative models with task-specific rewards at test time. Applying tree search to Masked Diffusion Language Models, however, introduces two key challenges: (i) parallel…

Computation and Language · Computer Science 2025-09-30 Zichao Yu , Ming Li , Wenyi Zhang , Weiguo Gao

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies have incorporated reward models to guide response selection…

Artificial Intelligence · Computer Science 2025-09-30 Feng Xiong , Hongling Xu , Yifei Wang , Runxi Cheng , Yong Wang , Xiangxiang Chu

We reproduce the central claims of Test-Time Training on Nearest Neighbors for Large Language Models (Hardt and Sun, 2024), which proposes adapting a language model at inference time by fine-tuning on retrieved nearest-neighbor sequences.…

Computation and Language · Computer Science 2025-11-24 Boyang Zhou , Johan Lindqvist , Lindsey Li

We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guiding the training policy towards a target policy with desired…

Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…

Computation and Language · Computer Science 2026-02-04 Brian Christian , Hannah Rose Kirk , Jessica A. F. Thompson , Christopher Summerfield , Tsvetomira Dumbalska

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

Machine Learning · Computer Science 2025-06-19 Xuerui Su , Shufang Xie , Guoqing Liu , Yingce Xia , Renqian Luo , Peiran Jin , Zhiming Ma , Yue Wang , Zun Wang , Yuting Liu

Self-improvement through post-training methods such as iterative preference learning has been acclaimed for enhancing the problem-solving capabilities (e.g., mathematical reasoning) of Large Language Models (LLMs) without human…

Computation and Language · Computer Science 2024-07-09 Ting Wu , Xuefeng Li , Pengfei Liu

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Artificial Intelligence · Computer Science 2025-11-26 Dominik Wagner , Leon Witzman , Luke Ong

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are then selected through best-of-$n$ (BoN) sampling or the LLM…

Machine Learning · Computer Science 2024-07-04 Adam X. Yang , Maxime Robeyns , Thomas Coste , Zhengyan Shi , Jun Wang , Haitham Bou-Ammar , Laurence Aitchison

External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection. At inference time, the model generates multiple reasoning paths, and an auxiliary process reward model (PRM) is used to score and…

Machine Learning · Computer Science 2025-05-26 Zeen Song , Wenwen Qiang , Siyu Zhao , Changwen Zheng , Gang Hua

Recent studies on post-training large language models (LLMs) for reasoning through reinforcement learning (RL) typically focus on tasks that can be accurately verified and rewarded, such as solving math problems. In contrast, our research…

Computation and Language · Computer Science 2025-05-29 Ang Lv , Ruobing Xie , Xingwu Sun , Zhanhui Kang , Rui Yan

Scaling up neural models has yielded significant advancements in a wide array of tasks, particularly in language generation. Previous studies have found that the performance of neural models frequently adheres to predictable scaling laws,…

Information Retrieval · Computer Science 2024-07-16 Yan Fang , Jingtao Zhan , Qingyao Ai , Jiaxin Mao , Weihang Su , Jia Chen , Yiqun Liu

Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the strong assumption that a reasoning system should always give…

Computation and Language · Computer Science 2025-07-21 William Jurayj , Jeffrey Cheng , Benjamin Van Durme

The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (RL). However, the architectural mechanisms behind such…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Minbyul Jeong , Jaewoo Kang

By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include…

Machine Learning · Computer Science 2023-12-01 Jared Markowitz , Jesse Silverberg , Gary Collins

Extreme value theory provides rigorous theory and statistical tools for extrapolation in machine learning, particularly in settings where traditional methods struggle due to data scarcity in the tails. A broad range of tasks benefit from…

Machine Learning · Statistics 2026-05-05 Sebastian Engelke , Nicola Gnecco , Anne Sabourin

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. How do language models of different sizes learn during pre-training? Why do larger…

Computation and Language · Computer Science 2023-05-31 Mengzhou Xia , Mikel Artetxe , Chunting Zhou , Xi Victoria Lin , Ramakanth Pasunuru , Danqi Chen , Luke Zettlemoyer , Ves Stoyanov

The problem of regression extrapolation, or out-of-distribution generalization, arises when predictions are required at test points outside the range of the training data. In such cases, the non-parametric guarantees for regression methods…

Methodology · Statistics 2024-10-31 Gloria Buriticá , Sebastian Engelke
‹ Prev 1 8 9 10 Next ›