Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.21933 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918356433502208 |
|---|---|
| author | Majumder, Bitan Sen, Anirban |
| author_facet | Majumder, Bitan Sen, Anirban |
| contents | Sarcasm detection in multilingual and code-mixed environments remains a challenging task for natural language processing models due to structural variations, informal expressions, and low-resource linguistic availability. This study compares four large language models, Llama 3.1, Mistral, Gemma 3, and Phi-4, with a fine-tuned DistilBERT model for sarcasm detection in code-mixed Hinglish text. The results indicate that the smaller, sequentially fine-tuned DistilBERT model achieved the highest overall accuracy of 84%, outperforming all of the LLMs in zero and few-shot set ups, using minimal LLM generated code-mixed data used for fine-tuning. These findings indicate that domain-adaptive fine-tuning of smaller transformer based models may significantly improve sarcasm detection over general LLM inference, in low-resource and data scarce settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21933 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Small Wins Big: Comparing Large Language Models and Domain Fine-Tuned Models for Sarcasm Detection in Code-Mixed Hinglish Text Majumder, Bitan Sen, Anirban Computation and Language Sarcasm detection in multilingual and code-mixed environments remains a challenging task for natural language processing models due to structural variations, informal expressions, and low-resource linguistic availability. This study compares four large language models, Llama 3.1, Mistral, Gemma 3, and Phi-4, with a fine-tuned DistilBERT model for sarcasm detection in code-mixed Hinglish text. The results indicate that the smaller, sequentially fine-tuned DistilBERT model achieved the highest overall accuracy of 84%, outperforming all of the LLMs in zero and few-shot set ups, using minimal LLM generated code-mixed data used for fine-tuning. These findings indicate that domain-adaptive fine-tuning of smaller transformer based models may significantly improve sarcasm detection over general LLM inference, in low-resource and data scarce settings. |
| title | Small Wins Big: Comparing Large Language Models and Domain Fine-Tuned Models for Sarcasm Detection in Code-Mixed Hinglish Text |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.21933 |