# GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO

arXiv: https://arxiv.org/abs/2506.08965 · HTML: https://mlsanity.com/paper/2506.08965/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 29 of its 58 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 29 of 29)

- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [V-STaR: Training Verifiers for Self-Taught Reasoners](https://mlsanity.com/paper/2402.06457/) (2024)
- [MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot](https://mlsanity.com/paper/2502.04413/) (2025)
- [Reinforcement Learning Enhanced LLMs: A Survey](https://mlsanity.com/paper/2412.10400/) (2024)
- [Active Preference Optimization for Sample Efficient RLHF](https://mlsanity.com/paper/2402.10500/) (2024)
- [Beyond Scalar Reward Model: Learning Generative Judge from Preference Data](https://mlsanity.com/paper/2410.03742/) (2024)
- [A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications](https://mlsanity.com/paper/2410.15595/) (2024)
- [Prototypical Reward Network for Data-Efficient RLHF](https://mlsanity.com/paper/2406.06606/) (2024)
- [Brain-inspired Search Engine Assistant based on Knowledge Graph](https://mlsanity.com/paper/2012.13529/) (2020)
- [A Smart Multimodal Healthcare Copilot with Powerful LLM Reasoning](https://mlsanity.com/paper/2506.02470/) (2025)

## Abstract (arXiv)

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that enables generative reward models trained on small datasets to achieve comparable performance to those trained on large-scale datasets. Traditional methods to train a generative reward model, such as Direct Preference Optimization (DPO), are constrained by inefficiencies in sample pairing and limited data diversity. This work introduces preference refinement, which employs Chain-of-Thought (CoT) sampling to uncover diverse and high-quality preference relationships. It also incorporates a perplexity-based scoring mechanism to assign nuanced preference levels and utilizes Multi-level Direct Preference Optimization (M-DPO) to enable the model to capture finer-grained preference differences between samples. Experimental results demonstrate that the proposed method significantly enhances data efficiency and model performance, enabling reward models trained in a few-shot setting to achieve results on par with those trained on large-scale datasets. This study underscores the potential of data-efficient strategies in advancing reward model optimization, offering a robust solution for low-resource RLHF applications.