Papers › GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization

GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization

26 Mar 2025arXiv:2503.20194archive 2025-07-28

Zhouhong Gu, Xingzhou Chen, Xiaoran Shi, Tao Wang, SuHang Zheng, Tianyu Li, Hongwei Feng, Yanghua Xiao

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response synthesis or preferential response optimization, they often struggle with constraint understanding and adaptation. This limitation becomes particularly evident when handling fine-grained constraints, leading to either hallucination or brittle performance. We introduce Generative Adversarial Policy Optimization (GAPO), a novel framework that combines GAN-based training dynamics with an encoder-only reward model to progressively learn and adapt to increasingly complex constraints. GAPO leverages adversarial training to automatically generate training samples of varying difficulty while utilizing the encoder-only architecture to better capture prompt-response relationships. Extensive experiments demonstrate GAPO's superior performance across multiple benchmarks, particularly in scenarios requiring fine-grained constraint handling, where it significantly outperforms existing methods like PPO, DPO, and KTO. Our results suggest that GAPO's unique approach to preferential prompt learning offers a more robust and effective solution for controlling LLM outputs. Code is avaliable in https://github.com/MikeGu721/GAPO.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mikegu721/gapo officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

HallucinationPrompt Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DPOEntropy RegularizationPPO

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections