Problem
Research questions and friction points this paper is trying to address.
multilingual
Multiple-Choice Question Answering
MCQA
cross-lingual
The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge
🤖 AI Summary
本文解决了多语言多项选择题问答问题，通过微调模型、应用多模态学习及构建无训练检索系统三种方法提高准确率。
📝 Abstract
This paper details the Eloquence team's approach to Task 2 of the 2nd MLC-SLM challenge at Interspeech 2026, which involves multilingual Multiple-Choice Question Answering (MCQA) across 21 languages. Three approaches are explored. First, we fine-tune Voxtral-Mini-3B via LoRA with cross-lingual data augmentation, ASR transcript augmentation and timestamp-aware audio cropping, achieving 0.72 macro-accuracy on evaluation Phase 2. Second, we apply multimodal in-context learning (ICL) to the frozen Voxtral-24B model to correct a strong label bias, reaching 0.81, our best result. Third, a training-free retrieval system based on a three-layer voice-anchored memory combining acoustic identity, semantic content, and a knowledge graph achieves 0.68. All three systems substantially outperform the official baseline.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multilingual MCQA
LoRA fine-tuning
cross-lingual data augmentation
multimodal in-context learning
voice-anchored memory
🔎 Similar Papers
No similar papers found.
