English
Related papers

Related papers: Preference Fine-Tuning of LLMs Should Leverage Sub…

200 papers

Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative…

Computation and Language · Computer Science 2025-07-25 Siqi Guo , Ilgee Hong , Vicente Balmaseda , Changlong Yu , Liang Qiu , Xin Liu , Haoming Jiang , Tuo Zhao , Tianbao Yang

In this article, we investigate the alignment of Large Language Models according to human preferences. We discuss the features of training a Preference Model, which simulates human preferences, and the methods and details we found essential…

Machine Learning · Computer Science 2024-10-03 Alexey Kutalev , Sergei Markoff

Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use, the way preference-based learning is applied varies wildly,…

Computation and Language · Computer Science 2024-10-10 Hamish Ivison , Yizhong Wang , Jiacheng Liu , Zeqiu Wu , Valentina Pyatkin , Nathan Lambert , Noah A. Smith , Yejin Choi , Hannaneh Hajishirzi

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a…

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2023-01-05 Daniel Shin , Anca D. Dragan , Daniel S. Brown

Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between…

Computation and Language · Computer Science 2025-03-25 Sharan Maiya , Yinhong Liu , Ramit Debnath , Anna Korhonen

Auto-evaluation is crucial for assessing response quality and offering feedback for model development. Recent studies have explored training large language models (LLMs) as generative judges to evaluate and critique other models' outputs.…

Computation and Language · Computer Science 2025-09-15 Peifeng Wang , Austin Xu , Yilun Zhou , Caiming Xiong , Shafiq Joty

In the absence of abundant reliable annotations for challenging tasks and contexts, how can we expand the frontier of LLM capabilities with potentially wrong answers? We focus on two research questions: (1) Can LLMs generate reliable…

Computation and Language · Computer Science 2024-10-16 Jihan Yao , Wenxuan Ding , Shangbin Feng , Lucy Lu Wang , Yulia Tsvetkov

Alignment techniques for LLMs rely on optimizing preference-based objectives -- where these preferences are typically elicited as ordinal, binary choices between responses. Recent work has focused on improving label quality or mitigating…

Artificial Intelligence · Computer Science 2025-08-13 Parker Whitfill , Stewy Slocum

This work focuses on leveraging and selecting from vast, unlabeled, open data to pre-fine-tune a pre-trained language model. The goal is to minimize the need for costly domain-specific data for subsequent fine-tuning while achieving desired…

Machine Learning · Computer Science 2024-05-07 Feiyang Kang , Hoang Anh Just , Yifan Sun , Himanshu Jahagirdar , Yuanzhi Zhang , Rongxing Du , Anit Kumar Sahu , Ruoxi Jia

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Machine Learning · Computer Science 2025-07-23 Debangshu Banerjee , Kintan Saha , Aditya Gopalan

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…

Computation and Language · Computer Science 2025-01-09 Shentao Yang , Shujian Zhang , Congying Xia , Yihao Feng , Caiming Xiong , Mingyuan Zhou

We present a method and dataset for fine-tuning language models with preference supervision using feedback-driven improvement chains. Given a model response, an annotator provides fine-grained feedback by marking ``liked'' and ``disliked''…

Computation and Language · Computer Science 2025-12-30 Sky CH-Wang , Justin Svegliato , Helen Appel , Jason Eisner

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

Machine Learning · Computer Science 2022-10-12 Rujie Zhong , Duohan Zhang , Lukas Schäfer , Stefano V. Albrecht , Josiah P. Hanna

Recommendation systems leverage user interaction data to suggest relevant items while filtering out irrelevant (negative) ones. The rise of large language models (LLMs) has garnered increasing attention for their potential in recommendation…

Information Retrieval · Computer Science 2025-08-14 Chenlu Ding , Daoxuan Liu , Jiancan Wu , Xingyu Hu , Junkang Wu , Haitao Wang , Yongkang Wang , Xingxing Wang , Xiang Wang

Preference tuning is a crucial process for aligning deep generative models with human preferences. This survey offers a thorough overview of recent advancements in preference tuning and the integration of human feedback. The paper is…

Computation and Language · Computer Science 2024-11-05 Genta Indra Winata , Hanyang Zhao , Anirban Das , Wenpin Tang , David D. Yao , Shi-Xiong Zhang , Sambit Sahu

Recent preference learning frameworks for large language models (LLMs) simplify human preferences with binary pairwise comparisons and scalar rewards. This simplification could make LLMs' responses biased to mostly preferred features, and…

Machine Learning · Computer Science 2025-06-16 Dongyoung Kim , Jinsung Yoon , Jinwoo Shin , Jaehyung Kim

Large language models (LLMs) generally utilize a consistent data distribution throughout the pretraining process. However, as the model's capability improves, it is intuitive that its data preferences dynamically change, indicating the need…

Computation and Language · Computer Science 2025-02-18 Xuemiao Zhang , Liangyu Xu , Feiyu Duan , Yongwei Zhou , Sirui Wang , Rongxiang Weng , Jingang Wang , Xunliang Cai

Recent research has shown that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) using only a small amount of parallel data. However, SFT simply instructs the model to imitate…

Computation and Language · Computer Science 2024-08-30 Dawei Zhu , Sony Trenous , Xiaoyu Shen , Dietrich Klakow , Bill Byrne , Eva Hasler

Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existing approaches rely on preference pairs constructed from model-generated images. Such…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Weiyan Chen , Weijian Deng , Yao Xiao , Weijie Tu , ZiYi Dong , Ibrahim Radwan , Liang Lin , Pengxu Wei