Skip to content

TEMA: Evidence-Grounded Temporal Question Answering in Multi-Turn Multi-Audio Dialogs

Sep 2026 · arXiv.org · Vol abs/2609.30029 · 0 citations · 17 references
Computer Science

Abstract

Multi-turn, multi-audio temporal question answering requires models to track target events across follow-up questions, recording switches, and historical references, recovering complete instances and their boundaries for temporal calculation and comparison. We propose TEMA, which connects event perception with evidence-based answering through Route, specifying the audio scope, and Span, describing all relevant intervals as conditional audio captions. We construct TEMA-Dialog with 40,704 dialogs and per-turn evidence and answer supervision, and TEMA-Bench for joint evaluation of evidence and final answers. Training combines temporal grounding initialization, full-dialog supervised fine-tuning, and completeness-first Span-only GRPO. Experiments on Qwen2.5-Omni and AF-Next show improved temporal question answering, particularly event localization and cross-audio comparison. Reinforcement learning applied solely to evidence further improves interval recovery and answer accuracy.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.