English
Related papers

Related papers: Does Self-Evaluation Enable Wireheading in Languag…

200 papers

As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense…

Machine Learning · Computer Science 2023-10-23 Elizabeth Bates , Vasilios Mavroudis , Chris Hicks

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

Exploring in environments with high-dimensional observations is hard. One promising approach for exploration is to use intrinsic rewards, which often boils down to estimating "novelty" of states, transitions, or trajectories with deep…

Machine Learning · Computer Science 2023-05-17 Toru Lin , Allan Jabri

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Computation and Language · Computer Science 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Artificial Intelligence · Computer Science 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

Machine Learning · Computer Science 2025-04-29 Zhaoyang Wang , Weilei He , Zhiyuan Liang , Xuchao Zhang , Chetan Bansal , Ying Wei , Weitong Zhang , Huaxiu Yao

Chain-of-thought reasoning, where language models expend additional computation by producing thinking tokens prior to final responses, has driven significant advances in model capabilities. However, training these reasoning models is…

Machine Learning · Computer Science 2026-03-20 Nived Rajaraman , Audrey Huang , Miro Dudik , Robert Schapire , Dylan J. Foster , Akshay Krishnamurthy

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

Computation and Language · Computer Science 2025-05-21 Jiaxin Guo , Zewen Chi , Li Dong , Qingxiu Dong , Xun Wu , Shaohan Huang , Furu Wei

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy…

Machine Learning · Computer Science 2026-04-29 Shuning Shang , Hubert Strauss , Stanley Wei , Sanjeev Arora , Noam Razin

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…

Computation and Language · Computer Science 2021-04-13 Zhengxu Hou , Bang Liu , Ruihui Zhao , Zijing Ou , Yafei Liu , Xi Chen , Yefeng Zheng

Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…

Machine Learning · Computer Science 2023-10-31 Joey Hong , Kush Bhatia , Anca Dragan

Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is ambiguous or expensive to obtain. We introduce Reinforcement…

Neural and Evolutionary Computing · Computer Science 2026-01-30 Micah Rentschler , Jesse Roberts

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Computation and Language · Computer Science 2024-12-12 Kaiyuan Chen , Jin Wang , Xuejie Zhang

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…

Machine Learning · Computer Science 2025-10-29 Ignavier Ng , Patrick Blöbaum , Siddharth Bhandari , Kun Zhang , Shiva Kasiviswanathan

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

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Computation and Language · Computer Science 2024-10-25 Vaskar Nath , Dylan Slack , Jeff Da , Yuntao Ma , Hugh Zhang , Spencer Whitehead , Sean Hendryx

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…

Computation and Language · Computer Science 2025-06-02 Shelly Bensal , Umar Jamil , Christopher Bryant , Melisa Russak , Kiran Kamble , Dmytro Mozolevskyi , Muayad Ali , Waseem AlShikh

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and…

Computation and Language · Computer Science 2024-11-28 Shijian Deng , Wentian Zhao , Yu-Jhe Li , Kun Wan , Daniel Miranda , Ajinkya Kale , Yapeng Tian

The success of Reinforcement Learning from Human Feedback (RLHF) critically depends on the quality of the reward model. However, while this quality is primarily evaluated through accuracy, it remains unclear whether accuracy fully captures…

Machine Learning · Computer Science 2026-03-02 Noam Razin , Zixuan Wang , Hubert Strauss , Stanley Wei , Jason D. Lee , Sanjeev Arora

Self-improvement is a mechanism in Large Language Model (LLM) pre-training, post-training and test-time inference. We explore a framework where the model verifies its own outputs, filters or reweights data based on this verification, and…

Computation and Language · Computer Science 2025-02-26 Yuda Song , Hanlin Zhang , Carson Eisenach , Sham Kakade , Dean Foster , Udaya Ghai
‹ Prev 1 4 5 6 7 8 10 Next ›