# Small Wins Big: Comparing Large Language Models and Domain Fine-Tuned Models for Sarcasm Detection in Code-Mixed Hinglish Text

arXiv: https://arxiv.org/abs/2602.21933 · HTML: https://mlsanity.com/paper/2602.21933/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Debiasing Multimodal Sarcasm Detection with Contrastive Learning](https://mlsanity.com/paper/2312.10493/) (2023)
- [News Headlines Dataset For Sarcasm Detection](https://mlsanity.com/paper/2212.06035/) (2022)

## Abstract (arXiv)

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.