SOURCE-LINKED INTELLIGENCE

SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

This paper describes our system for Task~2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge. We adapt Qwen3-Omni-30B-A3B-Instruct with a segment-evidence-aware data and post-training pipeline. A language model converts timestamped ASR into coherent event spans, which are expanded by a boundary margin and cropped from the original recording. We then synthesize complementary semantic MCQs with Qwen3.6-27B and acoustic MCQs with Gemini~3.1 Flash-Lite, followed by structural, grounding, answer-consistency, and target-model trainability checks, yielding 359,825 ve

Read original source ↗ Open in workspace

recordType

paper

region

Global