English
Related papers

Related papers: Automatically Finding Reward Model Biases

200 papers

Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and…

Computation and Language · Computer Science 2025-12-01 Fatima Kazi

This paper investigates the subtle and often concealed biases present in Large Language Models (LLMs), focusing on implicit biases that may remain despite passing explicit bias tests. Implicit biases are significant because they influence…

Computation and Language · Computer Science 2024-10-01 Serene Lim , María Pérez-Ortiz

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…

Large language models are known to hallucinate when faced with unfamiliar queries, but the underlying mechanism that govern how models hallucinate are not yet fully understood. In this work, we find that unfamiliar examples in the models'…

Machine Learning · Computer Science 2024-05-30 Katie Kang , Eric Wallace , Claire Tomlin , Aviral Kumar , Sergey Levine

When language model (LM) users aim to improve the quality of its generations, it is crucial to specify concrete behavioral attributes that the model should strive to reflect. However, curating such principles across many domains, even…

Computation and Language · Computer Science 2025-11-17 Keshav Ramji , Tahira Naseem , Ramón Fernandez Astudillo

Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it…

Computation and Language · Computer Science 2024-10-15 Zhaofeng Wu , Ananth Balashankar , Yoon Kim , Jacob Eisenstein , Ahmad Beirami

Reward design is central to reinforcement learning from human feedback (RLHF) and alignment research. In this work, we propose a unified framework to study hard, continuous, and hybrid reward structures for fine-tuning large language models…

Machine Learning · Computer Science 2025-11-18 Subramanyam Sahoo

This paper explores a top-down approach to automating incremental advances in machine learning research through component-level innovation, facilitated by Large Language Models (LLMs). Our framework systematically generates novel…

Machine Learning · Computer Science 2024-09-10 Shervin Ardeshir

In recent years, Large Language Models (LLMs) have witnessed a remarkable surge in prevalence, altering the landscape of natural language processing and machine learning. One key factor in improving the performance of LLMs is alignment with…

Computation and Language · Computer Science 2023-10-17 Keita Saito , Akifumi Wachi , Koki Wataoka , Youhei Akimoto

As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply…

Computers and Society · Computer Science 2026-01-13 Addison J. Wu , Ryan Liu , Xuechunzi Bai , Thomas L. Griffiths

The Bradley-Terry (BT) model is a common and successful practice in reward modeling for Large Language Model (LLM) alignment. However, it remains unclear why this model -- originally developed for multi-player stochastic game matching --…

Artificial Intelligence · Computer Science 2025-01-28 Hao Sun , Yunyi Shen , Jean-Francois Ton

Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases. This study introduces a novel evaluation framework to uncover gender biases in…

Computation and Language · Computer Science 2026-03-10 Evan Chen , Run-Jun Zhan , Yan-Bai Lin , Hung-Hsuan Chen

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Artificial Intelligence · Computer Science 2026-05-12 Katarzyna Kobalczyk , Mihaela van der Schaar

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotics, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives.…

Robotics · Computer Science 2026-01-09 Tony Lee , Andrew Wagenmaker , Karl Pertsch , Percy Liang , Sergey Levine , Chelsea Finn

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current…

Computation and Language · Computer Science 2026-05-04 Yufei Guo , Muzhe Guo , Juntao Su , Zhou Yang , Mengqiu Zhu , Hongfei Li , Mengyang Qiu , Shuo Shuo Liu

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Artificial Intelligence · Computer Science 2024-10-30 Long Tan Le , Han Shu , Tung-Anh Nguyen , Choong Seon Hong , Nguyen H. Tran

Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary,…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Machine Learning · Computer Science 2026-02-11 Pei-Chi Pan , Yingbin Liang , Sen Lin

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

Computation and Language · Computer Science 2026-03-09 Xiusi Chen , Gaotang Li , Ziqi Wang , Bowen Jin , Cheng Qian , Yu Wang , Hongru Wang , Yu Zhang , Denghui Zhang , Tong Zhang , Hanghang Tong , Heng Ji
‹ Prev 1 8 9 10 Next ›