In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912073287467008 |
|---|---|
| author | Shamshiri, Alireza Ryu, Kyeong Rok Park, June Young |
| author_facet | Shamshiri, Alireza Ryu, Kyeong Rok Park, June Young |
| contents | Large language models (LLMs) have achieved impressive results across various tasks. However, they still struggle with long-context documents. This study evaluates the performance of three leading LLMs: GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro on lengthy, complex, and opinion-varying documents concerning infrastructure projects, under both zero-shot and few-shot scenarios. Our results indicate that GPT-4o excels in zero-shot scenarios for simpler, shorter documents, while Claude 3.5 Sonnet surpasses GPT-4o in handling more complex, sentiment-fluctuating opinions. In few-shot scenarios, Claude 3.5 Sonnet outperforms overall, while GPT-4o shows greater stability as the number of demonstrations increases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11265 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinions Shamshiri, Alireza Ryu, Kyeong Rok Park, June Young Computation and Language Artificial Intelligence Large language models (LLMs) have achieved impressive results across various tasks. However, they still struggle with long-context documents. This study evaluates the performance of three leading LLMs: GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro on lengthy, complex, and opinion-varying documents concerning infrastructure projects, under both zero-shot and few-shot scenarios. Our results indicate that GPT-4o excels in zero-shot scenarios for simpler, shorter documents, while Claude 3.5 Sonnet surpasses GPT-4o in handling more complex, sentiment-fluctuating opinions. In few-shot scenarios, Claude 3.5 Sonnet outperforms overall, while GPT-4o shows greater stability as the number of demonstrations increases. |
| title | In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinions |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.11265 |