Efficient Multilingual Dialogue Processing via Translation Pipelines and Distilled Language Models

Abstract

This paper presents team Kl33n3x’s multilingual dialogue summarization and question answering system developed for the NLPAI4Health 2025 shared task. The approach employs a three-stage pipeline: forward translation from Indic languages to English, multitask text generation using a 2.55B parameter distilled language model, and reverse translation back to source languages. By leveraging knowledge distillation techniques, this work demonstrates that compact models can achieve highly competitive performance across nine languages. The system achieved strong win rates across the competition’s tasks, with particularly robust performance on Marathi (86.7% QnA), Tamil (86.7% QnA), and Hindi (80.0% QnA), demonstrating the effectiveness of translation-based approaches for low-resource language processing without task-specific fine-tuning.

Details

Author: Santiago Martínez Novoa, Nicolás Rozo Fajardo, Diego Alejandro González Vargas, Nicolás Bedoya Figueroa Year: 2026 Publication Type: Publication

Citation

Martínez Novoa, S., Rozo Fajardo, N., González Vargas, D. A., & Bedoya Figueroa, N. (2026). Efficient Multilingual Dialogue Processing via Translation Pipelines and Distilled Language Models. arXiv preprint arXiv:2601.09059.