# Instruction Quality Matters: Refining Instructions for Effective Preference Learning

arXiv: https://arxiv.org/abs/2608.26779 · HTML: https://mlsanity.com/paper/2608.26779/

## 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 21 of its 40 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [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)
- [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)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning](https://mlsanity.com/paper/2308.12032/) (2023)
- [Self-Boosting Large Language Models with Synthetic Preference Data](https://mlsanity.com/paper/2410.06961/) (2024)
- [Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment](https://mlsanity.com/paper/2406.04412/) (2024)
- [reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs](https://mlsanity.com/paper/2503.11751/) (2025)
- [ReIFE: Re-evaluating Instruction-Following Evaluation](https://mlsanity.com/paper/2410.07069/) (2024)
- [What Matters in Data for DPO?](https://mlsanity.com/paper/2508.18312/) (2025)
- [FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only](https://mlsanity.com/paper/2408.01323/) (2024)
- [Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora](https://mlsanity.com/paper/2408.12799/) (2024)

## Abstract (arXiv)

Preference learning optimizes models using response pairs, yet the informativeness of these pairs is fundamentally shaped by the instructions from which they are generated. We identify instruction quality as a hidden bottleneck in preference learning: low-quality or ambiguous instructions restrict the response-quality distribution, limiting strong chosen responses and weakening preference signals. Through Best- and Worst-of-N analyses, we show that instruction quality constrains both the ceiling and floor of sampled response quality. Motivated by this observation, we introduce an instruction-refinement pipeline that selects weak instructions using reward signals and revises them with rubric-guided LLM feedback, improving preference data without discarding examples. Across offline and online preference learning settings, experiments on multiple models and benchmarks show broad alignment improvements over original data and alternative data-improvement strategies. Further analyses indicate that instruction refinement raises achievable response quality and complements response-centric preference data curation. Overall, instruction quality emerges as a key factor governing how informative preference signals are formed for LLM alignment. Code is available at: https://github.com/01choco/instruction-refinement/