# Post-edits Are Preferences Too

arXiv: https://arxiv.org/abs/2410.02320 · HTML: https://mlsanity.com/paper/2410.02320/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [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)
- [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)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2309.11925/) (2023)
- [Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning](https://mlsanity.com/paper/1805.10627/) (2018)
- [Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training](https://mlsanity.com/paper/2307.08416/) (2023)

## Built on by (most cited first, 3 of 3)

- [Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs](https://mlsanity.com/paper/2506.17080/) (2025)
- [Steering Large Language Models for Machine Translation Personalization](https://mlsanity.com/paper/2505.16612/) (2025)
- [When Edit Localization Amplifies Relative Selection Bias: Gradient Geometry, Target Mismatch, and Importance Weighting](https://mlsanity.com/paper/2609.13709/) (2026)

## Abstract (arXiv)

Preference Optimization (PO) techniques are currently one of the state of the art techniques for fine-tuning large language models (LLMs) on pairwise preference feedback from human annotators. However, in machine translation, this sort of feedback can be difficult to solicit. Additionally, Kreutzer et al. (2018) have shown that, for machine translation, pairwise preferences are less reliable than other forms of human feedback, such as 5-point ratings. We examine post-edits to see if they can be a source of reliable human preferences by construction. In PO, a human annotator is shown sequences s1 and s2 and asked for a preference judgment, %s1 > s2; while for post-editing, editors create s1 and know that it should be better than s2. We attempt to use these implicit preferences for PO and show that it helps the model move towards post-edit-like hypotheses and away from machine translation-like hypotheses. Furthermore, we show that best results are obtained by pre-training the model with supervised fine-tuning (SFT) on post-edits in order to promote post-edit-like hypotheses to the top output ranks.