Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910983566393344 |
|---|---|
| author | Lepagnol, Pierre Ghannay, Sahar Gerald, Thomas Servan, Christophe Rosset, Sophie |
| author_facet | Lepagnol, Pierre Ghannay, Sahar Gerald, Thomas Servan, Christophe Rosset, Sophie |
| contents | Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the reliability of the considered system. Current State-of-the-Art SLU techniques rely on large amounts of training data; however, only limited annotated examples are available for specific tasks or languages.
In the meantime, instruction-tuned large language models (LLMs) have shown exceptional performance on unseen tasks in a few-shot setting when provided with adequate prompts. In this work, we propose to explore example selection by leveraging Information retrieval (IR) approaches to build an enhanced prompt that is applied to an SLU task. We evaluate the effectiveness of the proposed method on several SLU benchmarks. Experimental results show that lexical IR methods significantly enhance performance without increasing prompt length. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03035 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning Lepagnol, Pierre Ghannay, Sahar Gerald, Thomas Servan, Christophe Rosset, Sophie Computation and Language Artificial Intelligence Information Retrieval Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the reliability of the considered system. Current State-of-the-Art SLU techniques rely on large amounts of training data; however, only limited annotated examples are available for specific tasks or languages. In the meantime, instruction-tuned large language models (LLMs) have shown exceptional performance on unseen tasks in a few-shot setting when provided with adequate prompts. In this work, we propose to explore example selection by leveraging Information retrieval (IR) approaches to build an enhanced prompt that is applied to an SLU task. We evaluate the effectiveness of the proposed method on several SLU benchmarks. Experimental results show that lexical IR methods significantly enhance performance without increasing prompt length. |
| title | Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2506.03035 |