mlsanityData to 7 Oct 2026

ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent

arXiv 2403.04481 ↗First posted 7 Mar 2024cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level tasks, where the autoregressive nature of LLMs often leads to misalignment issues. They also struggle to capture nuanced interrelations in semantic-level tasks through direct fine-tuning alone. To address these challenges, we propose the Entity-level Language Model (ECLM) framework, which reformulates slot-filling as an entity recognition task and introduces a novel concept, textitChain of Intent, to enable step-by-step multi-intent recognition. Experimental results show that ECLM significantly outperforms strong baselines such as Uni-MIS, achieving gains of 3.7% on MixATIS and 3.1% on MixSNIPS. Compared to standard supervised fine-tuning of LLMs, ECLM further achieves improvements of 8.5% and 21.2% on these datasets, respectively. Our code is available at https://github.com/SJY8460/ECLM.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 13 of its 32 references that are in the map. First posted on arXiv 7 Mar 2024.

Builds on

13 of 32 references.

References · 13

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  3. 2016Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Fillingcited by 137
  4. 2019A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understandingcited by 106
  5. 2019A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Fillingcited by 85
  6. 2018Joint Slot Filling and Intent Detection via Capsule Neural Networkscited by 73
  7. 2020Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsingcited by 72
  8. 2020A Co-Interactive Transformer for Joint Slot Filling and Intent Detectioncited by 61
  9. 2018A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Fillingcited by 53
  10. 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
  11. 2019CM-Net: A Novel Collaborative Memory Network for Spoken Language Understandingcited by 34
  12. 2021GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Fillingcited by 33
1 more
  1. 2021Joint Multiple Intent Detection and Slot Filling via Self-distillationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Aligning Large Language Models via Fully Self-Synthetic Datacited by 3
  2. 2026Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answeringcited by 2
  3. 2025AFD-SLU: Adaptive Feature Distillation for Spoken Language Understandingcited by 1
  4. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0
  5. 2026Safety-Oriented Evaluation of Language Understanding Systems for Air Traffic Controlcited by 0
  6. 2026Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decompositioncited by 0
  7. 2026Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understandingcited by 0