# Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding

arXiv: https://arxiv.org/abs/2511.19005 · HTML: https://mlsanity.com/paper/2511.19005/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [End-to-End Slot Alignment and Recognition for Cross-Lingual NLU](https://mlsanity.com/paper/2004.14353/) (2020)
- [A Survey on Text Classification: From Shallow to Deep Learning](https://mlsanity.com/paper/2008.00364/) (2020)
- [A Co-Interactive Transformer for Joint Slot Filling and Intent Detection](https://mlsanity.com/paper/2010.03880/) (2020)
- [T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering](https://mlsanity.com/paper/2305.03453/) (2023)
- [AI Flow at the Network Edge](https://mlsanity.com/paper/2411.12469/) (2024)
- [Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought](https://mlsanity.com/paper/2403.05518/) (2024)
- [CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding](https://mlsanity.com/paper/1909.06937/) (2019)
- [A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding](https://mlsanity.com/paper/2304.04256/) (2023)
- [Spoken Language Understanding on the Edge](https://mlsanity.com/paper/1810.12735/) (2018)
- [PIN: A Novel Parallel Interactive Network for Spoken Language Understanding](https://mlsanity.com/paper/2009.13431/) (2020)
- [Towards Joint Intent Detection and Slot Filling via Higher-order Attention](https://mlsanity.com/paper/2109.08890/) (2021)
- [52B to 1T: Lessons Learned via Tele-FLM Series](https://mlsanity.com/paper/2407.02783/) (2024)
- [Technical Report of TeleChat2, TeleChat2.5 and T1](https://mlsanity.com/paper/2507.18013/) (2025)
- [JPIS: A Joint Model for Profile-based Intent Detection and Slot Filling with Slot-to-Intent Attention](https://mlsanity.com/paper/2312.08737/) (2023)

## Built on by (most cited first, 1 of 1)

- [Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges](https://mlsanity.com/paper/2512.11258/) (2025)

## Abstract (arXiv)

Spoken Language Understanding (SLU) consists of two sub-tasks: intent detection (ID) and slot filling (SF). Given its broad range of real-world applications, enhancing SLU for practical deployment is increasingly critical. Profile-based SLU addresses ambiguous user utterances by incorporating context awareness (CA), user profiles (UP), and knowledge graphs (KG) to support disambiguation, thereby advancing SLU research toward real-world applicability. However, existing SLU datasets still fall short in representing real-world scenarios. Specifically, (1) CA uses one-hot vectors for representation, which is overly idealized, and (2) models typically focuses solely on predicting intents and slot labels, neglecting the reasoning process that could enhance performance and interpretability. To overcome these limitations, we introduce VRSLU, a novel SLU dataset that integrates both Visual images and explicit Reasoning. For over-idealized CA, we use GPT-4o and FLUX.1-dev to generate images reflecting users' environments and statuses, followed by human verification to ensure quality. For reasoning, GPT-4o is employed to generate explanations for predicted labels, which are then refined by human annotators to ensure accuracy and coherence. Additionally, we propose an instructional template, LR-Instruct, which first predicts labels and then generates corresponding reasoning. This two-step approach helps mitigate the influence of reasoning bias on label prediction. Experimental results confirm the effectiveness of incorporating visual information and highlight the promise of explicit reasoning in advancing SLU.