paper-with-me

Papers

Self-Generative Adversarial Fine-Tuning for Large Language Models

2026-02-01 · Shiguang Wu, Yaqing Wang, Quanming Yao arxiv

Fine-tuning large language models (LLMs) for alignment typically relies on supervised fine-tuning or reinforcement learning from human feedback, both limited by the cost and scarcity of high-quality annotations. Recent self-play and synthetic data approaches reduce this dependence but often rely on heuristic assumptions or ungrounded self-evaluation, which can cause bias accumulation and performance drift. In this paper, we propose Self-Generative Adversarial LLM (SGALM), a unified fine-tuning framework that formulates alignment as a generative adversarial game within a single LLM. SGALM jointly evolves generation and discrimination capabilities without external reward models. Theoretical and empirical results demonstrate that SGALM achieves state-of-the-art performance, serves as an effective alignment algorithm and a robust synthetic data engine.

📄 PDF Abstract BibTeX arXiv:2602.01137

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy

2024-02-28 · Bashir Kazimi, Karina Ruzaeva, Stefan Sandfeld

In this work, we explore the potential of self-supervised learning with Generative Adversarial Networks (GANs) for electron microscopy datasets. We show how self-supervised pretraining facilitates efficient fine-tuning f…

DenoisingSelf-Supervised LearningSemantic SegmentationSuper-Resolution

Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning

2026-02-01 · Shangzhe Li, Xuchao Zhang, Chetan Bansal, Weitong Zhang arxiv

Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into strong language model without preference data. However, the theoretical foun…

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

2020-03-28 · CVPR 2020 6 · Tianlong Chen, Sijia Liu, Shiyu Chang, Yu Cheng 외

Pretrained models from self-supervision are prevalently used in fine-tuning downstream tasks faster or for better accuracy. However, gaining robustness from pretraining is left unexplored. We introduce adversarial traini…

Adversarial Robustness

Improving Adversarial Defense with Self-supervised Test-time Fine-tuning

2021-09-29 · Zhichao Huang, Chen Liu, Mathieu Salzmann, Sabine Süsstrunk 외

Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples. In thi…

Adversarial Defense

Self-Conditioned Generative Adversarial Networks for Image Editing

2022-02-08 · Yunzhe Liu, Rinon Gal, Amit H. Bermano, Baoquan Chen 외

Generative Adversarial Networks (GANs) are susceptible to bias, learned from either the unbalanced data, or through mode collapse. The networks focus on the core of the data distribution, leaving the tails - or the edges…

Fairness