compar:IA: The French Government's LLM arena to collect French-language human prompts and preference data

TL;DR

The paper introduces compar:IA, a French government-developed platform that collects large-scale French-language human preference data to improve multilingual LLMs, with open datasets and initial analyses.

Contribution

It presents an open-source infrastructure for collecting and analyzing French-language human preferences, addressing data scarcity in non-English LLM training.

Findings

Collected over 600,000 prompts and 250,000 preference votes

Released open datasets including conversations, votes, and reactions

Developed a French-language model leaderboard and analyzed user interaction patterns

Abstract

Large Language Models (LLMs) often show reduced performance, cultural alignment, and safety robustness in non-English languages, partly because English dominates both pre-training data and human preference alignment datasets. Training methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) require human preference data, which remains scarce and largely non-public for many languages beyond English. To address this gap, we introduce compar:IA, an open-source digital public service developed inside the French government and designed to collect large-scale human preference data from a predominantly French-speaking general audience. The platform uses a blind pairwise comparison interface to capture unconstrained, real-world prompts and user judgments across a diverse set of language models, while maintaining low participation friction and privacy-preserving automated filtering. As of 2026-02-07, compar:IA has collected over 600,000 free-form prompts and 250,000 preference votes, with approximately 89% of the data in French. We release three complementary datasets -- conversations, votes, and reactions -- under open licenses, and present initial analyses, including a French-language model leaderboard and user interaction patterns. Beyond the French context, compar:IA is evolving toward an international digital public good, offering reusable infrastructure for multilingual model training, evaluation, and the study of human-AI interaction.