Skip to results
MLSift
← Feed
NLP & Language ModelsFlow Matching2608.05785

Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation

Tirth Bhatt, Naren Kumar S, Mayank Singh

cs.CL cs.AI

Abstract

Multilingual text embedding models are commonly adapted using a single training objective across diverse tasks, despite different tasks requiring fundamentally different optimization strategies. We introduce Task-Conditional Flow Matching (TCFM), a multilingual embedding adaptation framework that selectively applies Flow Matching to translation tasks while optimizing retrieval, classification, and pair-classification tasks with objectives better aligned to their learning dynamics. TCFM further combines teacher-guided representation preservation with a three-stage curriculum to enable stable adaptation. Evaluated on the Indic Massive Text Embedding Benchmark, TCFM establishes a new state-of-the-art, consistently improving embedding quality across a diverse set of multilingual tasks and generalizing across embedding model families. We will publicly release the codebase and datasets upon acceptance of the paper.

Topics

Classified with taxonomy v2 on Wed, 2 Sept 2026.

The PDF is 1–3 MB. Open it in your browser's viewer, or load it here.

Open PDF