# Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning

arXiv: https://arxiv.org/abs/2411.02481 · HTML: https://mlsanity.com/paper/2411.02481/

## Key facts

- Cited by 1 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 30 of its 43 references that are in the map.
- First posted on arXiv 4 Nov 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, 30 of 30)

- [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 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [Iterative Reasoning Preference Optimization](https://mlsanity.com/paper/2404.19733/) (2024)
- [HelpSteer2: Open-source dataset for training top-performing reward models](https://mlsanity.com/paper/2406.08673/) (2024)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [A Minimaximalist Approach to Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2401.04056/) (2024)
- [DPO Meets PPO: Reinforced Token Optimization for RLHF](https://mlsanity.com/paper/2404.18922/) (2024)
- [Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss](https://mlsanity.com/paper/2312.16682/) (2023)
- [Contrastive Decoding Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2309.09117/) (2023)
- [Self-Taught Evaluators](https://mlsanity.com/paper/2408.02666/) (2024)
- [Bootstrapping Language Models with DPO Implicit Rewards](https://mlsanity.com/paper/2406.09760/) (2024)
- [Direct Judgement Preference Optimization](https://mlsanity.com/paper/2409.14664/) (2024)
- [On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization](https://mlsanity.com/paper/2409.03650/) (2024)
- [Distributional Preference Alignment of LLMs via Optimal Transport](https://mlsanity.com/paper/2406.05882/) (2024)
- [Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning](https://mlsanity.com/paper/2406.17312/) (2024)
- [In-Context Learning for Extreme Multi-Label Classification](https://mlsanity.com/paper/2401.12178/) (2024)

## Built on by (most cited first, 1 of 1)

- [Semi-Supervised Preference Optimization with Limited Feedback](https://mlsanity.com/paper/2511.00040/) (2025)

## Abstract (arXiv)

Preference tuning relies on high-quality human preference data, which is often expensive and time-consuming to gather. In this paper, we introduce Dr.SoW (Density Ratio of Strong over Weak) a cost-effective method that eliminates the reliance for human annotation by leveraging off-the-shelf LLMs for preference data annotation. Dr.SoW uses the log-density ratio between a better-aligned and a less-aligned LLM as a reward signal. We evaluate Dr.SoW across 221 different LLM pairs and empirically find a strong correlation between the performance gap of the paired models and the quality of the reward signal. This insight provides a practical guideline for selecting LLMs for data annotation. Additionally, we introduce an end-to-end pipeline that customizes reward functions based on user query domains. Without fine-tuning, it improves accuracy on domain-specific evaluations. With a pair of Mistral-7B models, Dr.SoW achieves a RewardBench score of 82.6, outperforming the best trained reward functions from same model class and demonstrating competitive performance against SoTA models in Safety (91.0) and Reasoning (88.0) domains. Further, we preference-tune Llama-3-8B-Instruct using data annotated by Dr.SoW. Our approach pushes Llama-3-8B to achieve a 37.4 % (+15.1 %) win rate on ArenaHard and a 40.7 % (+17.8 %) win rate on length-controlled AlpacaEval 2.0.