Thrilled to have my last two PhD papers accepted at COLING 2025!

1️⃣ “Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain”, where we study the efficacy of hybrid search across a variety of prominent retrieval models within the unexplored field of law in the French language, assessing both zero-shot and in-domain scenarios.

→ Paper: https://aclanthology.org/2025.coling-main.290

→ Code: https://github.com/maastrichtlawtech/fusion

→ Models: https://huggingface.co/collections/maastrichtlawtech/legal-neural-retrievers

2️⃣ “ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval”, where we present a modular dense retrieval model that learns from a single high-resource language (like English) and effectively transfers zero-shot to other languages, thereby eliminating the need for language-specific labeled retrieval data.

→ Paper: https://aclanthology.org/2025.coling-main.295

→ Code: https://github.com/ant-louis/xm-retrievers

→ Model: https://huggingface.co/antoinelouis/colbert-xm