paper-with-me

Papers

Active Preference Learning for Large Language Models

2024-02-12 · William Muldrew, Peter Hayes, Mingtian Zhang, David Barber

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model resources in the case where LLMs themselves are used as oracles. Reinforcement learning from Human or AI preferences (RLHF/RLAIF) is the most prominent example of such a technique, but is complex and often unstable. Direct Preference Optimization (DPO) has recently been proposed as a simpler and more stable alternative. In this work, we develop an active learning strategy for DPO to make better use of preference labels. We propose a practical acquisition function for prompt/completion pairs based on the predictive entropy of the language model and a measure of certainty of the implicit preference model optimized by DPO. We demonstrate how our approach improves both the rate of learning and final performance of fine-tuning on pairwise preference data.

📄 PDF Abstract BibTeX arXiv:2402.08114

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

DPO 설명 없음

Similar Papers 제목 키워드 기반

MAPLE: A Framework for Active Preference Learning Guided by Large Language Models

2024-12-10 · Saaduddin Mahmud, Mason Nakamura, Shlomo Zilberstein

The advent of large language models (LLMs) has sparked significant interest in using natural language for preference learning. However, existing methods often suffer from high computational burdens, taxing human supervis…

Active LearningLanguage ModelingLanguage ModellingLarge Language Model

Sample Efficient Preference Alignment in LLMs via Active Exploration

2023-12-01 · Viraj Mehta, Syrine Belakaria, Vikramjeet Das, Ojash Neopane 외

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, inc…

reinforcement-learningReinforcement Learning

AMPO: Active Multi-Preference Optimization

2025-02-25 · Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal 외

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language model…

Language ModelingLanguage Modelling

Active Preference Inference using Language Models and Probabilistic Reasoning

2023-12-19 · Wasu Top Piriyakulkij, Volodymyr Kuleshov, Kevin Ellis

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced ind…

Decision Making

Deep Bayesian Active Learning for Preference Modeling in Large Language Models

2024-06-14 · Luckeciano C. Melo, Panagiotis Tigas, Alessandro Abate, Yarin Gal

Leveraging human preferences for steering the behavior of Large Language Models (LLMs) has demonstrated notable success in recent years. Nonetheless, data selection and labeling are still a bottleneck for these systems, …

Active Learning