SFL-MTSC：利用语义框架级多任务自一致性实现鲁棒的多意图口语理解
SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding
AI总结：
提出语义框架级多任务自一致性（SFL-MTSC）框架，通过将预测分解为意图特定框架、进行域-意图分组和槽级聚类，并利用路径支持评分评估聚类可靠性，有效缓解多意图场景下基于提示的口语理解中的意图-槽结构不一致问题，在MAC-SLU基准上提升了槽F1和整体准确率。
摘要：
基于提示的大语言模型（LLMs）口语理解（SLU）常常由于解码随机性导致意图-槽结构不一致，尤其是在多意图场景中。鉴于此，我们提出了语义框架级多任务自一致性（SFL-MTSC），一种在语义框架层面运行的新型结构化聚合框架。与输出级多数投票不同，SFL-MTSC将预测分解为意图特定的框架，应用域-意图分组和槽级聚类，并使用路径支持评分评估聚类可靠性。保留可靠的框架并重新整合以形成最终预测。在MAC-SLU基准数据集上的零样本实验表明，与单路径推理相比，槽F1和整体准确率有所提高，而意图准确率在大多数设置下基本保持稳定。
英文摘要：
Prompt-based spoken language understanding (SLU) with large language models (LLMs) often suffers from inconsistent intent--slot structures due to decoding stochasticity, particularly in multi-intent scenarios. In view of this, we propose Semantic Frame-Level Multi-Task Self-Consistency (SFL-MTSC), a novel structured aggregation framework operating at the semantic frame level. Instead of output-level majority voting, SFL-MTSC decomposes predictions into intent-specific frames, applies domain--intent grouping and slot-level clustering, and evaluates cluster reliability using path support scoring. Reliable frames are retained and re-integrated to form the final prediction. Zero-shot experiments on the MAC-SLU benchmark dataset show improved slot F1 and overall accuracy over single-path inference, while intent accuracy remains largely stable across most settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
