Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain
This work addresses hybrid search for non-English specialized domains, specifically French law, providing insights that expand prior findings but are incremental in scope.
The paper investigated hybrid retrieval in French legal documents, finding that fusing different domain-general models consistently improved performance in zero-shot contexts, but fusion generally diminished performance when using in-domain trained models unless scores were carefully weighted.
Hybrid search has emerged as an effective strategy to offset the limitations of different matching paradigms, especially in out-of-domain contexts where notable improvements in retrieval quality have been observed. However, existing research predominantly focuses on a limited set of retrieval methods, evaluated in pairs on domain-general datasets exclusively in English. In this work, 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. Our findings reveal that in a zero-shot context, fusing different domain-general models consistently enhances performance compared to using a standalone model, regardless of the fusion method. Surprisingly, when models are trained in-domain, we find that fusion generally diminishes performance relative to using the best single system, unless fusing scores with carefully tuned weights. These novel insights, among others, expand the applicability of prior findings across a new field and language, and contribute to a deeper understanding of hybrid search in non-English specialized domains.