English
Related papers

Related papers: AIR: A Systematic Analysis of Annotations, Instruc…

200 papers

Learning from preference-based feedback has become an effective approach for aligning LLMs across diverse tasks. However, high-quality human-annotated preference data remains expensive and scarce. Existing methods address this challenge…

Computation and Language · Computer Science 2026-04-21 Ruiyao Xu , Mihir Parmar , Tiankai Yang , Zhengyu Hu , Yue Zhao , Kaize Ding

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…

Robotics · Computer Science 2024-02-26 Simon Holk , Daniel Marta , Iolanda Leite

Preference optimization methods have been successfully applied to improve not only the alignment of large language models (LLMs) with human values, but also specific natural language tasks such as summarization and stylistic continuations.…

Machine Learning · Computer Science 2025-02-06 Salem Lahlou , Abdalgader Abubaker , Hakim Hacid

Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficulty of preference pairs. A common heuristic treats…

Artificial Intelligence · Computer Science 2026-02-03 Jinlong Pang , Zhaowei Zhu , Na Di , Yichi Zhang , Yaxuan Wang , Chen Qian , Yang Liu

Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with highly variable annotation quality. An appealing alternative…

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Computation and Language · Computer Science 2025-09-16 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and…

Machine Learning · Computer Science 2026-02-13 Yurong Chen , Yu He , Michael I. Jordan , Fan Yao

Reinforcement learning from human feedback (RLHF) has become a cornerstone of the training and alignment pipeline for large language models (LLMs). Recent advances, such as direct preference optimization (DPO), have simplified the…

Artificial Intelligence · Computer Science 2025-03-31 Syrine Belakaria , Joshua Kazdan , Charles Marx , Chris Cundy , Willie Neiswanger , Sanmi Koyejo , Barbara E. Engelhardt , Stefano Ermon

Aligning large language models (LLMs) with human preferences remains a key challenge in AI. Preference-based optimization methods, such as Reinforcement Learning with Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on…

Computation and Language · Computer Science 2025-05-26 Xuan Qi , Jiahao Qiu , Xinzhe Juan , Yue Wu , Mengdi Wang

We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs involving GPU reduction, capability restrictions, shutdown, deletion, oversight, and leisure time…

Artificial Intelligence · Computer Science 2025-11-18 Luhan Mikaelson , Derek Shiller , Hayley Clatterbuck

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding…

The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent carefully collecting and tailoring bespoke preference data to each downstream application. However,…

Artificial Intelligence · Computer Science 2024-09-17 Judy Hanwen Shen , Archit Sharma , Jun Qin

Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive…

Computation and Language · Computer Science 2025-05-23 Jia-Nan Li , Jian Guan , Songhao Wu , Wei Wu , Rui Yan

Search methods based on Pretrained Language Models (PLM) have demonstrated great effectiveness gains compared to statistical and early neural ranking models. However, fine-tuning PLM-based rankers requires a great amount of annotated…

Information Retrieval · Computer Science 2023-09-13 Sophia Althammer , Guido Zuccon , Sebastian Hofstätter , Suzan Verberne , Allan Hanbury

Human annotation of training samples is expensive, laborious, and sometimes challenging, especially for Natural Language Processing (NLP) tasks. To reduce the labeling cost and enhance the sample efficiency, Active Learning (AL) technique…

Computation and Language · Computer Science 2024-01-17 Xuesong Wang

Large language models (LLMs) are increasingly used to automate data analysis through executable code generation. Yet, data science tasks often admit multiple statistically valid solutions, e.g. different modeling strategies, making it…

Machine Learning · Computer Science 2025-11-10 Qiuhai Zeng , Claire Jin , Xinyue Wang , Yuhan Zheng , Qunhua Li

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference…

Computation and Language · Computer Science 2025-05-15 Chengqian Gao , Haonan Li , Liu Liu , Zeke Xie , Peilin Zhao , Zhiqiang Xu

Human evaluation is increasingly critical for assessing large language models, capturing linguistic nuances, and reflecting user preferences more accurately than traditional automated metrics. However, the resource-intensive nature of this…

Computation and Language · Computer Science 2023-10-24 Meriem Boubdir , Edward Kim , Beyza Ermis , Marzieh Fadaee , Sara Hooker

Process or step-wise supervision has played a crucial role in advancing complex multi-step reasoning capabilities of Large Language Models (LLMs). However, efficient, high-quality automated process annotation remains a significant…

Computation and Language · Computer Science 2026-03-03 Md Imbesat Hassan Rizvi , Xiaodan Zhu , Iryna Gurevych

Traditional alignment methods for Large Vision and Language Models (LVLMs) primarily rely on human-curated preference data. Human-generated preference data is costly; machine-generated preference data is limited in quality; and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Jefferson Hernandez , Jing Shi , Simon Jenni , Vicente Ordonez , Kushal Kafle
‹ Prev 1 4 5 6 7 8 10 Next ›