# Fine-tuning Language Models with Generative Adversarial Reward Modelling

arXiv: https://arxiv.org/abs/2305.06176 · HTML: https://mlsanity.com/paper/2305.06176/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 9 May 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Inverse Reward Design](https://mlsanity.com/paper/1711.02827/) (2017)
- [A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2001.06937/) (2020)
- [Can we trust the evaluation on ChatGPT?](https://mlsanity.com/paper/2303.12767/) (2023)
- [Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues](https://mlsanity.com/paper/2012.09673/) (2020)
- [Improving GAN Training with Probability Ratio Clipping and Sample Reweighting](https://mlsanity.com/paper/2006.06900/) (2020)
- [Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback](https://mlsanity.com/paper/2303.02891/) (2023)

## Built on by (most cited first, 8 of 8)

- [Creativity Has Left the Chat: The Price of Debiasing Language Models](https://mlsanity.com/paper/2406.05587/) (2024)
- [Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data](https://mlsanity.com/paper/2409.11423/) (2024)
- [LLM Misalignment via Adversarial RLHF Platforms](https://mlsanity.com/paper/2503.03039/) (2025)
- [Adversarial Suffix Filtering: a Defense Pipeline for LLMs](https://mlsanity.com/paper/2505.09602/) (2025)
- [Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction](https://mlsanity.com/paper/2511.17879/) (2025)
- [Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training](https://mlsanity.com/paper/2507.08284/) (2025)
- [Self-Generative Adversarial Fine-Tuning for Large Language Models](https://mlsanity.com/paper/2602.01137/) (2026)
- [Pretrained Persona Mixture Models and Tandem Models for Human Simulation](https://mlsanity.com/paper/2609.22607/) (2026)

## Abstract (arXiv)

Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF is constrained by the expertise and productivity limitations of human evaluators. A response to this downside is to fall back to supervised fine-tuning (SFT) with additional carefully selected expert demonstrations. However, while this method has been proven to be effective, it invariably also leads to increased human-in-the-loop overhead. In this study, we propose another alternative approach: Reinforcement Learning with Generative Adversarial Feedback (RLGAF) to RLHF and SFT, which uses a generative adversarial training style to enable the LLMs to learn useful human expert demonstrations without being directly exposed to the training examples, thus enabling good generalization capabilities while preserving sample efficiency. Our preliminary findings indicate that RLGAF can help align LLMs outputs with competitive performance against RLHF and SFT, while not suffering from their respective inherent restrictions, suggesting promising avenues for further research on automating AI alignment.