arXiv cs.CL· Wenchao Du, Fangxin Shang, Long Wu, Runze Cui, Qing Yang, Yehui Yang·· 14 小时前AI 评分29
DecisionTraceBench：追踪多方语音对话中的决策关键信息
DecisionTraceBench: Tracking Decision-Critical Information in Multi-Party Spoken Conversations
AI 导读
研究团队推出语音状态追踪基准 DecisionTraceBench，用于评估决策关键信息状态追踪（DCIST），联合考察决策事件序列、说话人归属、范围与时间证据，并以轨迹级 F1 衡量完整事件链的还原。
正文 · 原文
Abstract:In high-stakes domains such as finance, critical information evolves through multi-party interaction. Recovering these changes and their sources is fundamental to reliable speech understanding. Existing speech benchmarks focus on transcription, local understanding, and turn-level state prediction, leaving joint decision evolution across speakers insufficiently evaluated. We introduce DecisionTraceBench, a speech state-tracking benchmark for Decision-Critical Information State Tracking (DCIST). It jointly evaluates decision event sequences, speaker attribution, scope, and temporal evidence, using trajectory-level F1 to measure complete event-chain recovery. Our dataset comprises Chinese financial dialogues involving two to four speakers, with 100.39 hours of synthetic audio and 8.61 hours of human-performed recordings. On a fixed cohort of human-performed recordings, five cascaded systems and two direct-audio models achieve DCIST scores of 5.73% to 21.35%. Ablations with speaker-labeled reference scripts and no temporal localization requirements yield a maximum score of only 38.72%. Audio perturbation experiments further show that overall transcription error rates do not adequately reflect complete trajectory recovery. These findings reveal limitations in jointly understanding information provenance and state evolution, providing a benchmark for evaluating decision-process understanding and decision traceability in high-stakes speech applications.
| Comments: | Project repository: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.34746 [cs.CL] |
| (or arXiv:2610.34746v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34746 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenchao Du [view email]
[v1]
Mon, 26 Oct 2026 02:46:07 UTC (1,309 KB)
来源：arXiv cs.CL · arxiv.org