English
Related papers

Related papers: REWARD CONSISTENCY: Improving Multi-Objective Alig…

200 papers

Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of…

Machine Learning · Computer Science 2023-10-11 Kaiwen Zha , Peng Cao , Jeany Son , Yuzhe Yang , Dina Katabi

Aligning large language models (LLMs) to human preferences is challenging in domains where preference data is unavailable. We address the problem of learning reward models for such target domains by leveraging feedback collected from…

Machine Learning · Computer Science 2025-01-03 David Wu , Sanjiban Choudhury

As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objective in trustworthy AI. This challenge becomes even more…

Machine Learning · Computer Science 2026-05-12 Hefei Xu , Le Wu , Yu Wang , Min Hou , Han Wu , Zhen Zhang , Meng Wang

Despite the prevalence of retrieval-augmented language models (RALMs), the seamless integration of these models with retrieval mechanisms to enhance performance in document-based tasks remains challenging. While some post-retrieval…

Computation and Language · Computer Science 2024-06-05 Chuankai Xu , Dongming Zhao , Bo Wang , Hanwen Xing

Reward design has been one of the central challenges for real world reinforcement learning (RL) deployment, especially in settings with multiple objectives. Preference-based RL offers an appealing alternative by learning from human…

Artificial Intelligence · Computer Science 2026-02-25 Chenyang Zhao , Vinny Cahill , Ivana Dusparic

To date, the multi-objective optimization literature has mainly focused on conflicting objectives, studying the Pareto front, or requiring users to balance tradeoffs. Yet, in machine learning practice, there are many scenarios where such…

Machine Learning · Computer Science 2025-03-05 Yonathan Efroni , Ben Kretzu , Daniel Jiang , Jalaj Bhandari , Zheqing , Zhu , Karen Ullrich

Collecting high-quality preference datasets for reinforcement learning from human feedback (RLHF) is resource-intensive and challenging. As a result, researchers often train reward models on extensive offline datasets which aggregate…

Machine Learning · Computer Science 2024-12-17 Shambhavi Krishna , Aishwarya Sahoo

Reward models (RMs) are central to the alignment of language models (LMs). An RM often serves as a proxy for human preferences to guide downstream LM behavior. However, our understanding of RM behavior is limited. Our work (i) formalizes a…

Computation and Language · Computer Science 2025-10-09 Elle

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Machine Learning · Computer Science 2023-11-02 Han Shao , Lee Cohen , Avrim Blum , Yishay Mansour , Aadirupa Saha , Matthew R. Walter

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…

Machine Learning · Computer Science 2026-02-17 Seongho Son , William Bankes , Sangwoong Yoon , Shyam Sundhar Ramesh , Xiaohang Tang , Ilija Bogunovic

A central belief in scaling reinforcement learning with verifiable rewards for instruction following (IF) tasks is that, a diverse mixture of verifiable hard and unverifiable soft constraints is essential for generalizing to unseen…

Machine Learning · Computer Science 2026-01-14 Yirong Zeng , Yufei Liu , Xiao Ding , Yutai Hou , Yuxian Wang , Haonan Song , Wu Ning , Dandan Tu , Qixun Zhang , Bibo Cai , Yuxiang He , Ting Liu

We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before training. It is challenging to identify appropriate constraint specifications due to the undefined…

Optimization and Control · Mathematics 2024-01-02 Dongsheng Ding , Zhengyan Huan , Alejandro Ribeiro

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Machine Learning · Computer Science 2025-08-07 Jinghang Han , Jiawei Chen , Hang Shao , Hao Ma , Mingcheng Li , Xintian Shen , Lihao Zheng , Wei Chen , Tao Wei , Lihua Zhang

Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale. While…

Machine Learning · Computer Science 2026-05-26 Payel Bhattacharjee , Osvaldo Simeone , Ravi Tandon

Reward models (RMs) are central to aligning large language models, yet their practical effectiveness hinges on generalization to unseen prompts and shifting distributions. Most existing RM evaluations rely on static, pre-annotated…

Computation and Language · Computer Science 2026-01-27 Shunyang Luo , Peibei Cao , Zhihui Zhu , Kehua Feng , Zhihua Wang , Keyan Ding

Conversational Recommender Systems (CRS) actively elicit user preferences to generate adaptive recommendations. Mainstream reinforcement learning-based CRS solutions heavily rely on handcrafted reward functions, which may not be aligned…

Information Retrieval · Computer Science 2023-11-01 Zhendong Chu , Nan Wang , Hongning Wang

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

Computation and Language · Computer Science 2025-10-14 Shuai Zhao , Yunqiu Xu , Linchao Zhu , Yi Yang

Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…

Computation and Language · Computer Science 2026-04-09 Qiyao Ma , Dechen Gao , Rui Cai , Boqi Zhao , Hanchu Zhou , Junshan Zhang , Zhe Zhao

Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward…

Machine Learning · Computer Science 2026-05-19 Mingxi Zou , Jiaxiang Chen , Junfan Li , Langzhang Liang , Qifan Wang , Xu Yinghui , Zenglin Xu

RL-based techniques can be employed to search for prompts that, when fed into a target language model, maximize a set of user-specified reward functions. However, in many target applications, the natural reward functions are in tension with…

Computation and Language · Computer Science 2025-06-10 Yasaman Jafari , Dheeraj Mekala , Rose Yu , Taylor Berg-Kirkpatrick