paper-with-me

Papers

Enhancing Preference-based Linear Bandits via Human Response Time

2024-09-09 · Shen Li, Yuyang Zhang, Zhaolin Ren, Claire Liang, Na Li, Julie A. Shah

Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference strength. To address this, we leverage human response times, which are inversely related to preference strength, as an additional signal. We propose a computationally efficient method that combines choices and response times to estimate human utility functions, grounded in the EZ diffusion model from psychology. Theoretical and empirical analyses show that for queries with strong preferences, response times complement choices by providing extra information about preference strength, leading to significantly improved utility estimation. We incorporate this estimator into preference-based linear bandits for fixed-budget best-arm identification. Simulations on three real-world datasets demonstrate that using response times significantly accelerates preference learning compared to choice-only approaches. Additional materials, such as code, slides, and talk video, are available at https://shenlirobot.github.io/pages/NeurIPS24.html

📄 PDF Abstract BibTeX arXiv:2409.05798

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions

2026-07-03 · Zihao Hu, Yuan Yao, Jiheng Zhang, Zhengyuan Zhou arxiv

Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can change over time, while user preference…

Human Preferences as Dueling Bandits

2022-04-21 · Xinyi Yan, Chengxi Luo, Charles L. A. Clarke, Nick Craswell 외

The dramatic improvements in core information retrieval tasks engendered by neural rankers create a need for novel evaluation methods. If every ranker returns highly relevant items in the top ranks, it becomes difficult …

Information RetrievalOnline Ranker EvaluationRetrieval

Active Human Feedback Collection via Neural Contextual Dueling Bandits

2025-04-16 · Arun Verma, Xiaoqiang Lin, Zhongxiang Dai, Daniela Rus 외

Collecting human preference feedback is often expensive, leading recent works to develop principled algorithms to select them more efficiently. However, these works assume that the underlying reward function is linear, a…

Optimizing Preference Alignment with Differentiable NDCG Ranking

2024-10-17 · Jiacong Zhou, Xianyun Wang, Jun Yu

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

Learning-To-Rank

Prompt Optimization with Human Feedback

2024-05-27 · Xiaoqiang Lin, Zhongxiang Dai, Arun Verma, See-Kiong Ng 외

Large language models (LLMs) have demonstrated remarkable performances in various tasks. However, the performance of LLMs heavily depends on the input prompt, which has given rise to a number of recent works on prompt op…