MAPLE: A Framework for Active Preference Learning Guided by Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929641705439232 |
|---|---|
| author | Mahmud, Saaduddin Nakamura, Mason Zilberstein, Shlomo |
| author_facet | Mahmud, Saaduddin Nakamura, Mason Zilberstein, Shlomo |
| contents | 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 supervision, and lack of interpretability. To address these issues, we introduce MAPLE, a framework for large language model-guided Bayesian active preference learning. MAPLE leverages LLMs to model the distribution over preference functions, conditioning it on both natural language feedback and conventional preference learning feedback, such as pairwise trajectory rankings. MAPLE also employs active learning to systematically reduce uncertainty in this distribution and incorporates a language-conditioned active query selection mechanism to identify informative and easy-to-answer queries, thus reducing human burden. We evaluate MAPLE's sample efficiency and preference inference quality across two benchmarks, including a real-world vehicle route planning benchmark using OpenStreetMap data. Our results demonstrate that MAPLE accelerates the learning process and effectively improves humans' ability to answer queries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07207 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MAPLE: A Framework for Active Preference Learning Guided by Large Language Models Mahmud, Saaduddin Nakamura, Mason Zilberstein, Shlomo Machine Learning Artificial Intelligence Computation and Language 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 supervision, and lack of interpretability. To address these issues, we introduce MAPLE, a framework for large language model-guided Bayesian active preference learning. MAPLE leverages LLMs to model the distribution over preference functions, conditioning it on both natural language feedback and conventional preference learning feedback, such as pairwise trajectory rankings. MAPLE also employs active learning to systematically reduce uncertainty in this distribution and incorporates a language-conditioned active query selection mechanism to identify informative and easy-to-answer queries, thus reducing human burden. We evaluate MAPLE's sample efficiency and preference inference quality across two benchmarks, including a real-world vehicle route planning benchmark using OpenStreetMap data. Our results demonstrate that MAPLE accelerates the learning process and effectively improves humans' ability to answer queries. |
| title | MAPLE: A Framework for Active Preference Learning Guided by Large Language Models |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2412.07207 |