Problem
Research questions and friction points this paper is trying to address.
multilingual text embedding
task adaptation
optimization strategy
embedding quality
Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation
🤖 AI Summary
Existing multilingual text embedding models typically employ a single training objective across diverse tasks, overlooking the fundamental differences in their optimization requirements. This work proposes the Task-Conditional Flow Matching (TCFM) framework, which introduces a task-conditional mechanism to tailor optimization objectives according to task-specific learning dynamics: leveraging flow matching for translation while designing more suitable objectives for retrieval, classification, and other tasks. The approach further integrates teacher-guided representations with a three-stage curriculum learning strategy to enable stable and efficient multitask adaptation. Evaluated on the Indic Massive Text Embedding Benchmark, TCFM achieves a new state of the art, significantly enhancing embedding quality across a wide range of multilingual tasks and demonstrating strong generalization across different model families.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Task-Conditional Flow Matching
Multilingual Text Embedding
Flow Matching
Curriculum Learning
Representation Preservation
🔎 Similar Papers
No similar papers found.
