English
Related papers

Related papers: Beyond RLHF and NLHF: Population-Proportional Alig…

200 papers

Ranking and comparing items is crucial for collecting information about preferences in many areas, from marketing to politics. The Mallows rank model is among the most successful approaches to analyse rank data, but its computational…

Methodology · Statistics 2017-04-28 Valeria Vitelli , Øystein Sørensen , Marta Crispino , Arnoldo Frigessi , Elja Arjas

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

Preference learning has gained significant attention in tasks involving subjective human judgments, such as \emph{speech emotion recognition} (SER) and image aesthetic assessment. While pairwise frameworks such as RankNet offer robust…

Machine Learning · Computer Science 2025-08-14 Abinay Reddy Naini , Fernando Diaz , Carlos Busso

Deployed supervised machine learning models make predictions that interact with and influence the world. This phenomenon is called performative prediction by Perdomo et al. (ICML 2020). It is an ongoing challenge to understand the influence…

Machine Learning · Computer Science 2022-02-24 Gavin Brown , Shlomi Hod , Iden Kalemaj

In this paper we extend the principle of proportional representation to rankings. We consider the setting where alternatives need to be ranked based on approval preferences. In this setting, proportional representation requires that…

Computer Science and Game Theory · Computer Science 2016-12-06 Piotr Skowron , Martin Lackner , Markus Brill , Dominik Peters , Edith Elkind

We present a novel unified bilevel optimization-based framework, \textsf{PARL}, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning using utility or preference-based feedback. We…

Machine Learning · Computer Science 2024-05-02 Souradip Chakraborty , Amrit Singh Bedi , Alec Koppel , Dinesh Manocha , Huazheng Wang , Mengdi Wang , Furong Huang

Aligning large language models with human preferences is essential for improving interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback…

Information Retrieval · Computer Science 2025-12-17 Jiacong Zhou , Xianyun Wang , Min Zhang , Jun Yu

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning…

Machine Learning · Computer Science 2025-05-14 Taehyun Cho , Seokhun Ju , Seungyub Han , Dohyeong Kim , Kyungjae Lee , Jungwoo Lee

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

Neural Combinatorial Optimization (NCO) has mostly focused on learning policies, typically neural networks, that operate on a single candidate solution at a time, either by constructing one from scratch or iteratively improving it. In…

Neural and Evolutionary Computing · Computer Science 2026-01-14 Andoni Irazusta Garmendia , Josu Ceberio , Alexander Mendiburu

Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…

Human-Computer Interaction · Computer Science 2026-01-29 Sarvesh Shashidhar , Abhishek Mishra , Madhav Kotecha

With ever-increasing available data, predicting individuals' preferences and helping them locate the most relevant information has become a pressing need. Understanding and predicting preferences is also important from a fundamental point…

Physics and Society · Physics 2012-10-05 Roger Guimera , Alejandro Llorente , Esteban Moro , Marta Sales-Pardo

An important aspect of AI design and ethics is to create systems that reflect aggregate preferences of the society. To this end, the techniques of social choice theory are often utilized. We propose a new social choice function motivated by…

Multiagent Systems · Computer Science 2021-03-02 Gergei Bana , Wojciech Jamroga , David Naccache , Peter Y. A. Ryan

We introduce a constrained priority mechanism that combines outcome-based matching from machine-learning with preference-based allocation schemes common in market design. Using real-world data, we illustrate how our mechanism could be…

General Economics · Economics 2020-08-13 Avidit Acharya , Kirk Bansak , Jens Hainmueller

We propose a scalable Bayesian preference learning method for jointly predicting the preferences of individuals as well as the consensus of a crowd from pairwise labels. Peoples' opinions often differ greatly, making it difficult to predict…

Machine Learning · Computer Science 2019-12-13 Edwin Simpson , Iryna Gurevych

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

Computation and Language · Computer Science 2026-05-19 Xuan Qi , Rongwu Xu , Zhijing Jin

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

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

Artificial Intelligence · Computer Science 2026-05-27 Dongyoon Hahm , Dylan Hadfield-Menell , Kimin Lee

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

Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and likelihood displacement, which can be driven by the noisy…

Computation and Language · Computer Science 2025-10-28 Peter Chen , Xi Chen , Wotao Yin , Tianyi Lin