How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908426623254528 |
|---|---|
| author | Wang, Mengqi Feng, Tiantian Narayanan, Shrikanth |
| author_facet | Wang, Mengqi Feng, Tiantian Narayanan, Shrikanth |
| contents | Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains challenging, particularly for subjective tasks like emotion recognition. Inspired by the SLT 2024 GenSER Challenge, this study investigates approaches to improving conversational emotion recognition (CER) by LLMs. Specifically, we explore how to retrieve high-quality examples in in-context learning (ICL) to enhance CER. We propose various strategies based on random and augmented example retrieval and also analyze the impact of conversational context on CER accuracy. Experiments were conducted on the three datasets including IEMOCAP, MELD and EmoryNLP. The results show that augmented example retrieval consistently outperforms other techniques under investigation across all datasets, highlighting the importance of retrieving coherent targeted examples and enhancing them through paraphrasing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models? Wang, Mengqi Feng, Tiantian Narayanan, Shrikanth Computation and Language Artificial Intelligence Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains challenging, particularly for subjective tasks like emotion recognition. Inspired by the SLT 2024 GenSER Challenge, this study investigates approaches to improving conversational emotion recognition (CER) by LLMs. Specifically, we explore how to retrieve high-quality examples in in-context learning (ICL) to enhance CER. We propose various strategies based on random and augmented example retrieval and also analyze the impact of conversational context on CER accuracy. Experiments were conducted on the three datasets including IEMOCAP, MELD and EmoryNLP. The results show that augmented example retrieval consistently outperforms other techniques under investigation across all datasets, highlighting the importance of retrieving coherent targeted examples and enhancing them through paraphrasing. |
| title | How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models? |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.20199 |