# Reward Difference Optimization For Sample Reweighting In Offline RLHF

arXiv: https://arxiv.org/abs/2408.09385 · HTML: https://mlsanity.com/paper/2408.09385/

## Key facts

- Cited by 10 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 23 of its 36 references that are in the map.
- First posted on arXiv 18 Aug 2024.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [Preference Ranking Optimization for Human Alignment](https://mlsanity.com/paper/2306.17492/) (2023)
- [Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study](https://mlsanity.com/paper/2404.10719/) (2024)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Provably Robust DPO: Aligning Language Models with Noisy Feedback](https://mlsanity.com/paper/2403.00409/) (2024)
- [Language Model Alignment with Elastic Reset](https://mlsanity.com/paper/2312.07551/) (2023)
- [What Makes Pre-trained Language Models Better Zero-shot Learners?](https://mlsanity.com/paper/2209.15206/) (2022)

## Built on by (most cited first, 10 of 10)

- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Larger or Smaller Reward Margins to Select Preferences for Alignment?](https://mlsanity.com/paper/2503.01864/) (2025)
- [Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs](https://mlsanity.com/paper/2506.10054/) (2025)
- [RePO: Understanding Preference Learning Through ReLU-Based Optimization](https://mlsanity.com/paper/2503.07426/) (2025)
- [More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning](https://mlsanity.com/paper/2510.07169/) (2025)
- [daDPO: Distribution-Aware DPO for Distilling Conversational Abilities](https://mlsanity.com/paper/2506.15717/) (2025)
- [ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning](https://mlsanity.com/paper/2508.19996/) (2025)
- [Adaptive Margin RLHF via Preference over Preferences](https://mlsanity.com/paper/2509.22851/) (2025)
- [Reverse Constitutional AI: A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIF](https://mlsanity.com/paper/2604.17769/) (2026)
- [Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines](https://mlsanity.com/paper/2605.26442/) (2026)

## Abstract (arXiv)

With the rapid advances in Large Language Models (LLMs), aligning LLMs with human preferences become increasingly important. Although Reinforcement Learning with Human Feedback (RLHF) proves effective, it is complicated and highly resource-intensive. As such, offline RLHF has been introduced as an alternative solution, which directly optimizes LLMs with ranking losses on a fixed preference dataset. Current offline RLHF only captures the "ordinal relationship" between responses, overlooking the crucial aspect of how much one is preferred over the others. To address this issue, we propose a simple yet effective solution called Reward Difference Optimization, shorted as RDO. Specifically, we introduce reward difference coefficients to reweigh sample pairs in offline RLHF. We then develop a difference model which captures rich interactions between a pair of responses for predicting these difference coefficients. Experiments with 7B LLMs on the HH and TL;DR datasets substantiate the effectiveness of our method in both automatic metrics and human evaluation, thereby highlighting its potential for aligning LLMs with human intent and values