# CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences

arXiv: https://arxiv.org/abs/2511.07691 · HTML: https://mlsanity.com/paper/2511.07691/

## 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 25 of its 35 references that are in the map.
- First posted on arXiv 10 Nov 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, 25 of 25)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.16039/) (2023)
- [Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment](https://mlsanity.com/paper/2402.19085/) (2024)
- [A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods](https://mlsanity.com/paper/2104.00054/) (2021)
- [The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://mlsanity.com/paper/2406.18682/) (2024)
- [MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization](https://mlsanity.com/paper/2401.06838/) (2024)
- [Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2412.14516/) (2024)
- [On the Blind Spots of Model-Based Evaluation Metrics for Text Generation](https://mlsanity.com/paper/2212.10020/) (2022)
- [MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset](https://mlsanity.com/paper/2010.04480/) (2020)
- [RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs](https://mlsanity.com/paper/2407.02552/) (2024)
- [X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale](https://mlsanity.com/paper/2410.03115/) (2024)
- [Language Imbalance Driven Rewarding for Multilingual Self-improving](https://mlsanity.com/paper/2410.08964/) (2024)
- [Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment](https://mlsanity.com/paper/2404.12318/) (2024)
- [M-IFEval: Multilingual Instruction-Following Evaluation](https://mlsanity.com/paper/2502.04688/) (2025)
- [A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques](https://mlsanity.com/paper/2406.04879/) (2024)
- [DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages](https://mlsanity.com/paper/2205.12215/) (2022)

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

- [MTQ-Eval: Multilingual Text Quality Evaluation for Language Models](https://mlsanity.com/paper/2511.09374/) (2025)
- [CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations](https://mlsanity.com/paper/2605.26293/) (2026)
- [Choosing the Right Language Mode at Inference Time for Multilingual Reliability](https://mlsanity.com/paper/2609.04653/) (2026)

## Abstract (arXiv)

Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have proven effective in English, they often fail to generalize robustly to multilingual settings. We propose a simple yet effective alternative, Confidence-Aware Preference Optimization (CAPO), which replaces DPO's fixed treatment of preference pairs with a dynamic loss scaling mechanism based on a relative reward. By modulating the learning signal according to the confidence in each preference pair, CAPO enhances robustness to noisy or low-margin comparisons, typically encountered in multilingual text. Empirically, CAPO outperforms existing preference optimization baselines by at least 16% in reward accuracy, and improves alignment by widening the gap between preferred and dispreferred responses across languages.