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

arXiv: https://arxiv.org/abs/2403.04481 · HTML: https://mlsanity.com/paper/2403.04481/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1609.01454/) (2016)
- [A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding](https://mlsanity.com/paper/1909.02188/) (2019)
- [A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1907.00390/) (2019)
- [Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1812.09471/) (2018)
- [Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2010.03546/) (2020)
- [A Co-Interactive Transformer for Joint Slot Filling and Intent Detection](https://mlsanity.com/paper/2010.03880/) (2020)
- [A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling](https://mlsanity.com/paper/1812.10235/) (2018)
- [A Survey on Spoken Language Understanding: Recent Advances and New Frontiers](https://mlsanity.com/paper/2103.03095/) (2021)
- [CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding](https://mlsanity.com/paper/1909.06937/) (2019)
- [GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling](https://mlsanity.com/paper/2106.01925/) (2021)
- [Joint Multiple Intent Detection and Slot Filling via Self-distillation](https://mlsanity.com/paper/2108.08042/) (2021)

## Built on by (most cited first, 7 of 7)

- [Aligning Large Language Models via Fully Self-Synthetic Data](https://mlsanity.com/paper/2510.06652/) (2025)
- [Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering](https://mlsanity.com/paper/2605.12645/) (2026)
- [AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding](https://mlsanity.com/paper/2509.04821/) (2025)
- [Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges](https://mlsanity.com/paper/2512.11258/) (2025)
- [Safety-Oriented Evaluation of Language Understanding Systems for Air Traffic Control](https://mlsanity.com/paper/2605.11769/) (2026)
- [Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition](https://mlsanity.com/paper/2607.14769/) (2026)
- [Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understanding](https://mlsanity.com/paper/2608.24621/) (2026)

## 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.