mlsanityData to 7 Oct 2026

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

arXiv 2606.25552 ↗First posted 24 Jun 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Audio-language model reasoning

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

22 of 31 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Qwen2.5-Omni Technical Report26 Mar

Other references · 21

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  5. 2024A Survey on LLM-as-a-Judgecited by 1,384
  6. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  7. 2025Confidence Improves Self-Consistency in LLMscited by 111
  8. 2024Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Taskscited by 102
  9. 2024Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Samplingcited by 63
  10. 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
  11. 2023A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understandingcited by 31
  12. 2023Better patching using LLM prompting, via Self-Consistencycited by 29
9 more
  1. 2022WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Modelscited by 25
  2. 2024Intent Detection in the Age of LLMscited by 25
  3. 2026vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Modelscited by 15
  4. 2024Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understandingcited by 4
  5. 2022A Unified Framework for Multi-intent Spoken Language Understanding with promptingcited by 3
  6. 2024CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understandingcited by 3
  7. 2023HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understandingcited by 2
  8. 2025Estimating the Self-Consistency of LLMscited by 2
  9. 2025MAC-SLU: Multi-Intent Automotive Cabin Spoken Language Understanding Benchmarkcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark
  2. 2025Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding
  3. 2026Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models
  4. 2025M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models
  5. 2024Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting
  6. 2026CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
  7. 2025Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization
  8. 2024MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)