English
Related papers

Related papers: Compositional preference models for aligning LMs

200 papers

Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual prompt. Despite recent progress, existing approaches either…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Wenyi Mo , Tianyu Zhang , Yalong Bai , Ligong Han , Ying Ba , Dimitris N. Metaxas

We present Preference Flow Matching (PFM), a new framework for preference-based reinforcement learning (PbRL) that streamlines the integration of preferences into an arbitrary class of pre-trained models. Existing PbRL methods require…

Machine Learning · Computer Science 2024-10-29 Minu Kim , Yongsik Lee , Sehyeok Kang , Jihwan Oh , Song Chong , Se-Young Yun

Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves…

Computation and Language · Computer Science 2025-11-26 Yixin Liu , Pengfei Liu , Arman Cohan

Large language models (LLMs) are very performant connectionist systems, but do they exhibit more compositionality? More importantly, is that part of why they perform so well? We present empirical analyses across four LLM families (12…

Computation and Language · Computer Science 2025-05-21 Ruchira Dhar , Anders Søgaard

Preference learning in Large Language Models (LLMs) has advanced significantly, yet existing methods remain limited by modest performance gains, high computational costs, hyperparameter sensitivity, and insufficient modeling of global…

Computation and Language · Computer Science 2026-04-03 Liang Zhu , Yuelin Bai , Xiankun Ren , Jiaxi Yang , Lei Zhang , Feiteng Fang , Hamid Alinejad-Rokny , Minghuan Tan , Min 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

Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and inefficient-motivating the need for efficient data selection methods that reduce annotation costs…

Computation and Language · Computer Science 2026-04-21 Seohyeong Lee , Eunwon Kim , Hwaran Lee , Buru Chang

Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. Prompts can be represented by a human-engineered word sequence or by a learned continuous embedding. In…

Computation and Language · Computer Science 2023-07-06 Jonathan Pilault , Can Liu , Mohit Bansal , Markus Dreyer

Large Language Models (LLMs) have demonstrated exceptional capabilities in generalizing to new tasks in a zero-shot or few-shot manner. However, the extent to which LLMs can comprehend user preferences based on their previous behavior…

Information Retrieval · Computer Science 2023-05-12 Wang-Cheng Kang , Jianmo Ni , Nikhil Mehta , Maheswaran Sathiamoorthy , Lichan Hong , Ed Chi , Derek Zhiyuan Cheng

Personalizing large language models (LLMs) is important for aligning outputs with diverse user preferences, yet existing methods struggle with flexibility and generalization. We propose CoPL (Collaborative Preference Learning), a…

Machine Learning · Computer Science 2025-09-18 Youngbin Choi , Seunghyuk Cho , Minjong Lee , MoonJeong Park , Yesong Ko , Jungseul Ok , Dongwoo Kim

Cumulative probability models (CPMs) are a robust alternative to linear models for continuous outcomes. However, they are not feasible for very large datasets due to elevated running time and memory usage, which depend on the sample size,…

Computation · Statistics 2022-07-15 Chun Li , Guo Chen , Bryan E. Shepherd

Large language models demonstrate impressive reasoning abilities but struggle to provide personalized content due to their lack of individual user preference information. Existing methods, such as in-context learning and parameter-efficient…

Computation and Language · Computer Science 2024-12-10 Sumuk Shashidhar , Abhinav Chinta , Vaibhav Sahai , Dilek Hakkani-Tür

While Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, aligning these models with varying human preferences across multiple objectives remains a significant challenge…

Computation and Language · Computer Science 2025-11-17 Biao Liu , Ning Xu , Junming Yang , Xin Geng

Can large language models (LLMs) learn a decision maker's preferences from observed choices and generate preference-consistent recommendations in new situations? We propose a portable Simulate-Recommend-Evaluate framework that tests…

General Economics · Economics 2026-04-08 Jeongbin Kim , Matthew Kovach , Kyu-Min Lee , Euncheol Shin , Hector Tzavellas

Preference learning provides a promising solution to address the limitations of supervised fine-tuning (SFT) for code language models, where the model is not explicitly trained to differentiate between correct and incorrect code. Recent…

Computation and Language · Computer Science 2024-10-15 Dylan Zhang , Shizhe Diao , Xueyan Zou , Hao Peng

Comparative reasoning plays a crucial role in text preference prediction; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning. While approaches like Chain-of-Thought improve accuracy in many other…

Human feedback plays a pivotal role in aligning large language models (LLMs) with human preferences. However, such feedback is often noisy or inconsistent, which can degrade the quality of reward models and hinder alignment. While various…

Artificial Intelligence · Computer Science 2025-10-15 Samuel Yeh , Sharon Li

Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training and system prompts appear to shape much of their behaviour. But models can also…

Computation and Language · Computer Science 2026-05-19 Oscar Gilg , Pierre Beckmann , Daniel Paleka , Patrick Butlin

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxiliary models or…

Computation and Language · Computer Science 2025-06-13 Hee Suk Yoon , Eunseop Yoon , Mark Hasegawa-Johnson , Sungwoong Kim , Chang D. Yoo

Recent advances in language modeling have underscored the role of preference feedback in enhancing model performance. This paper investigates the conditions under which preference feedback improves parameter estimation in classes of…

Machine Learning · Statistics 2025-05-30 Marc Jourdan , Gizem Yüce , Nicolas Flammarion