English
Related papers

Related papers: Meta-Aligner: Bidirectional Preference-Policy Opti…

200 papers

Large Language Models (LLMs) are increasingly deployed across diverse applications that demand balancing multiple, often conflicting, objectives -- such as helpfulness, harmlessness, or humor. Many traditional methods for aligning outputs…

Machine Learning · Computer Science 2026-02-17 Jeremy Carleton , Debajoy Mukherjee , Srinivas Shakkottai , Dileep Kalathil

Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic forgetting, where models lose previously acquired knowledge…

Computation and Language · Computer Science 2026-04-09 Junsong Li , Jie Zhou , Bihao Zhan , Yutao Yang , Qianjun Pan , Shilian Chen , Tianyu Huai , Xin Li , Qin Chen , Liang He

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Artificial Intelligence · Computer Science 2025-05-27 Anirudhan Badrinath , Prabhat Agarwal , Jiajing Xu

Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often deploy only one or a…

Neural and Evolutionary Computing · Computer Science 2024-01-05 Ke Li , Han Guo

Alignment training is crucial for enabling large language models (LLMs) to cater to human intentions and preferences. It is typically performed based on two stages with different objectives: instruction-following alignment and…

Computation and Language · Computer Science 2024-06-24 Chenglong Wang , Hang Zhou , Kaiyan Chang , Bei Li , Yongyu Mu , Tong Xiao , Tongran Liu , Jingbo Zhu

Most existing recommender systems represent a user's preference with a feature vector, which is assumed to be fixed when predicting this user's preferences for different items. However, the same vector cannot accurately capture a user's…

Information Retrieval · Computer Science 2019-08-22 Fan Liu , Zhiyong Cheng , Changchang Sun , Yinglong Wang , Liqiang Nie , Mohan Kankanhalli

Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majority of work to-date has focused on first-class citizen…

Computation and Language · Computer Science 2024-07-04 John Dang , Arash Ahmadian , Kelly Marchisio , Julia Kreutzer , Ahmet Üstün , Sara Hooker

When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong…

Machine Learning · Computer Science 2025-06-03 Nicholas E. Corrado , Julian Katz-Samuels , Adithya Devraj , Hyokun Yun , Chao Zhang , Yi Xu , Yi Pan , Bing Yin , Trishul Chilimbi

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Machine Learning · Computer Science 2025-09-09 Thanh Thi Nguyen , Campbell Wilson , Janis Dalins

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…

Computation and Language · Computer Science 2025-06-05 Honggen Zhang , Xufeng Zhao , Igor Molybog , June Zhang

Large Language Models (LLMs) are expected to produce safe, helpful, and honest content during interaction with human users, but they frequently fail to align with such values when given flawed instructions, e.g., missing context, ambiguous…

Computation and Language · Computer Science 2025-08-07 Feifan Song , Bofei Gao , Yifan Song , Yi Liu , Weimin Xiong , Yuyang Song , Tianyu Liu , Guoyin Wang , Houfeng Wang

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…

Computation and Language · Computer Science 2025-01-09 Hritik Bansal , Ashima Suvarna , Gantavya Bhatt , Nanyun Peng , Kai-Wei Chang , Aditya Grover

Multimodal Large Language Models (MLLMs) emerge as a unified interface to address a multitude of tasks, ranging from NLP to computer vision. Despite showcasing state-of-the-art results in many benchmarks, a long-standing issue is the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Alberto Compagnoni , Davide Caffagni , Nicholas Moratelli , Lorenzo Baraldi , Marcella Cornia , Rita Cucchiara

Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance…

Artificial Intelligence · Computer Science 2025-04-25 Yuran Li , Jama Hussein Mohamud , Chongren Sun , Di Wu , Benoit Boulet

Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective…

Machine Learning · Computer Science 2024-12-10 Subhojyoti Mukherjee , Anusha Lalitha , Sailik Sengupta , Aniket Deshmukh , Branislav Kveton

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

Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from…

Machine Learning · Computer Science 2025-12-09 Moxin Li , Yuantao Zhang , Wenjie Wang , Wentao Shi , Zhuo Liu , Fuli Feng , Tat-Seng Chua

Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most…

Machine Learning · Computer Science 2024-02-27 Tianchi Cai , Xierui Song , Jiyan Jiang , Fei Teng , Jinjie Gu , Guannan Zhang

Ensuring Large Language Models (LLMs) align with diverse human preferences while preserving privacy and fairness remains a challenge. Existing methods, such as Reinforcement Learning from Human Feedback (RLHF), rely on centralized data…

Machine Learning · Computer Science 2025-03-14 Mahmoud Srewa , Tianyu Zhao , Salma Elmalaki

Meta-reinforcement learning (Meta-RL) has attracted attention due to its capability to enhance reinforcement learning (RL) algorithms, in terms of data efficiency and generalizability. In this paper, we develop a bilevel optimization…

Machine Learning · Computer Science 2024-10-15 Siyuan Xu , Minghui Zhu