# SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding

arXiv: https://arxiv.org/abs/2606.25552 · HTML: https://mlsanity.com/paper/2606.25552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 22 of 22)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Confidence Improves Self-Consistency in LLMs](https://mlsanity.com/paper/2502.06233/) (2025)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling](https://mlsanity.com/paper/2408.17017/) (2024)
- [A Survey on Spoken Language Understanding: Recent Advances and New Frontiers](https://mlsanity.com/paper/2103.03095/) (2021)
- [A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding](https://mlsanity.com/paper/2304.04256/) (2023)
- [Better patching using LLM prompting, via Self-Consistency](https://mlsanity.com/paper/2306.00108/) (2023)
- [WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models](https://mlsanity.com/paper/2203.15863/) (2022)
- [Intent Detection in the Age of LLMs](https://mlsanity.com/paper/2410.01627/) (2024)
- [vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Models](https://mlsanity.com/paper/2602.02204/) (2026)
- [Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding](https://mlsanity.com/paper/2406.15209/) (2024)
- [A Unified Framework for Multi-intent Spoken Language Understanding with prompting](https://mlsanity.com/paper/2210.03337/) (2022)
- [CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding](https://mlsanity.com/paper/2406.10505/) (2024)
- [HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding](https://mlsanity.com/paper/2301.02010/) (2023)
- [Estimating the Self-Consistency of LLMs](https://mlsanity.com/paper/2509.19489/) (2025)
- [MAC-SLU: Multi-Intent Automotive Cabin Spoken Language Understanding Benchmark](https://mlsanity.com/paper/2512.01603/) (2025)

## Abstract (arXiv)

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.