English
Related papers

Related papers: RLVF: Learning from Verbal Feedback without Overge…

200 papers

Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans…

Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most…

Computation and Language · Computer Science 2023-11-06 Banghua Zhu , Hiteshi Sharma , Felipe Vieira Frujeri , Shi Dong , Chenguang Zhu , Michael I. Jordan , Jiantao Jiao

Reinforcement learning with human feedback (RLHF) has become the dominant method to align large models to user preferences. Unlike fine-tuning, for which there are many studies regarding training data memorization, it is not clear how…

Machine Learning · Computer Science 2024-10-28 Aneesh Pappu , Billy Porter , Ilia Shumailov , Jamie Hayes

The Reinforcement Learning from Human Feedback (RLHF) plays a pivotal role in shaping the impact of large language models (LLMs), contributing significantly to controlling output toxicity and selecting output styles, particularly as LLMs…

Artificial Intelligence · Computer Science 2023-08-11 Miao Fan , Chen Hu , Shuchang Zhou

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large…

Machine Learning · Computer Science 2024-10-11 Victor Zhong , Dipendra Misra , Xingdi Yuan , Marc-Alexandre Côté

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

Computation and Language · Computer Science 2025-04-22 Omar Shaikh , Michelle S. Lam , Joey Hejna , Yijia Shao , Hyundong Cho , Michael S. Bernstein , Diyi Yang

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly challenging for AI to understand human intentions and…

Computation and Language · Computer Science 2024-06-18 Rong Bao , Rui Zheng , Shihan Dou , Xiao Wang , Enyu Zhou , Bo Wang , Qi Zhang , Liang Ding , Dacheng Tao

Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternative is Direct Policy Optimization (DPO), which replaces an…

Computation and Language · Computer Science 2024-06-03 Runsheng Yu , Yong Wang , Xiaoqi Jiao , Youzhi Zhang , James T. Kwok

As large language models (LLMs) are increasingly deployed in diverse user facing applications, aligning them with real user preferences becomes essential. Existing methods like Reinforcement Learning from Human Feedback (RLHF) rely on…

Effective emotional support hinges on understanding users' emotions and needs to provide meaningful comfort during multi-turn interactions. Large Language Models (LLMs) show great potential for expressing empathy; however, they often…

Computation and Language · Computer Science 2025-05-23 Jing Ye , Lu Xiang , Yaping Zhang , Chengqing Zong

Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective…

Computation and Language · Computer Science 2023-10-12 Hannah Rose Kirk , Andrew M. Bean , Bertie Vidgen , Paul Röttger , Scott A. Hale

Bias in Large Language Models (LLMs) poses significant risks to trustworthiness, manifesting primarily as stereotypical biases (e.g., gender or racial stereotypes) and structural biases (e.g., lexical overlap or position preferences).…

Computation and Language · Computer Science 2025-12-30 Xuan Feng , Bo An , Tianlong Gu , Liang Chang , Fengrui Hao , Peipeng Yu , Shuai Zhao

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive. RL from AI Feedback (RLAIF), introduced in…

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Computation and Language · Computer Science 2023-10-03 Tianci Xue , Ziqi Wang , Heng Ji

Pretrained language models often do not perform tasks in ways that are in line with our preferences, e.g., generating offensive text or factually incorrect summaries. Recent work approaches the above issue by learning from a simple form of…

Computation and Language · Computer Science 2022-11-18 Jérémy Scheurer , Jon Ander Campos , Jun Shern Chan , Angelica Chen , Kyunghyun Cho , Ethan Perez

Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted descriptions, while real-world user inputs during inference…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Jiale Cheng , Ruiliang Lyu , Xiaotao Gu , Xiao Liu , Jiazheng Xu , Yida Lu , Jiayan Teng , Zhuoyi Yang , Yuxiao Dong , Jie Tang , Hongning Wang , Minlie Huang

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…

Machine Learning · Computer Science 2025-12-30 Timo Kaufmann , Paul Weng , Viktor Bengs , Eyke Hüllermeier

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

Computation and Language · Computer Science 2024-02-14 Víctor Gallego