---
title: "CUET-823 at MAHED 2025 Shared Task: Large Language"
description: "The paper describes the CUET-823 entry to Subtask-2 of the MAHED 2025 Shared Task. 19 references, cited by 1 paper here."
authors: ["Ratnajit Dhar", "Arpita Mallik"]
year: 2025
venue: "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks"
source: "https://aclanthology.org/2025.arabicnlp-sharedtasks.84/"
doi: "10.18653/v1/2025.arabicnlp-sharedtasks.84"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/dhar-2025-cuet-823-mahed-2025-shared/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/dhar-2025-cuet-823-mahed-2025-shared/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/14/) / CUET-823 at MAHED 2025 Shared Task: Large Language Model-Based Framework for Emotion, Offensive, and Hate Detection in Arabic

# CUET-823 at MAHED 2025 Shared Task: Large Language Model-Based Framework for Emotion, Offensive, and Hate Detection in Arabic

**Authors:** [Ratnajit Dhar](https://md.research.elamur.ai/free/en/authors/ratnajit-dhar/) and [Arpita Mallik](https://md.research.elamur.ai/free/en/authors/arpita-mallik/) · **Year:** 2025 · **Venue:** [Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2025](https://md.research.elamur.ai/free/en/venues/arabicnlp/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.arabicnlp-sharedtasks.84/) · [PDF](https://aclanthology.org/2025.arabicnlp-sharedtasks.84.pdf) · [DOI 10.18653/v1/2025.arabicnlp-sharedtasks.84](https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.84) · [OpenAlex](https://openalex.org/W4416037621)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/dhar-2025-cuet-823-mahed-2025-shared/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper describes the CUET-823 entry to Subtask-2 of the MAHED 2025 Shared Task. The subtask asks for three labels on short Arabic social media posts, mostly tweets: an emotion from 12 classes, an offensive yes/no decision, and a hate decision that applies only to offensive posts. The authors split the problem into two separately fine-tuned stages, both built on Meta-Llama-3.1-8B. The first stage predicts the emotion. The second gives a two-part answer: offensive or not, then hate, not_hate, or not_applicable. Training used 4-bit quantization and LoRA through Unsloth, with only the official MAHED 2025 data and no class balancing. On the hidden test set the system scored a macro F1 of 0.518, ranking 4th, and had the best precision of all teams. On the validation set, fine-tuning beat zero-shot and few-shot prompting, and LLaMA-3.1-8B came out ahead of several other small open models. The work shows that a modest, cheaply adapted LLM can handle hierarchical, imbalanced, dialect-rich classification with little data.

## Key points
- Data is the MAHED 2025 dataset. Of the 5,960 training posts, 1,744 are offensive and 303 are hate; the 1,277 validation posts include 363 that are offensive and 68 that are hate; a further 1,278 posts without labels form the test split. The emotion classes are very skewed, from anger at 1,551 down to fear at 53.
- Setup: Meta-Llama-3.1-8B, 4-bit (BitsAndBytes), LoRA rank 16, AdamW at lr 2e-4, 1000 steps for the emotion model and 500 for the offensive/hate model, and a 2048-token cap. Tools were Unsloth, Hugging Face Transformers, and TRL. Decoding used temperature 0.
- Test results: macro F1 0.518 (4th place) and precision 0.617, the top precision among participants.
- On validation, fine-tuned LLaMA-3.1-8B reached 0.554 macro F1, against 0.484 zero-shot and 0.477 few-shot. Mistral 7B v0.3, Qwen-2 7B, CodeGemma 7B, Zephyr 7B and Gemma 3 4B all scored lower.
- The paper claims conditional prompting beats flat multi-label classification, but the text reports no flat baseline numbers.
- The main errors were offensive posts not escalated to hate when the hate was implicit or culturally coded, and polite thanks labeled neutral instead of love.

## Interesting ideas
- The output has a fixed hierarchical slot format in which the dependent label is written as an explicit not_applicable when its parent is negative, so every answer has the same shape and stays easy to parse.
- Each stage gets its own prompt and its own adapter rather than one model that predicts everything at once, which lets each stage focus on different cues.
- The full closed label inventory goes into the prompt, and decoding is deterministic at temperature 0, which makes runs reproducible and keeps answers inside the label set.
- The same model family is compared in zero-shot, few-shot and fine-tuned modes on one dev set, which separates what adaptation contributes from what the base model contributes.
- The error analysis separates surface politeness from real affection and explicit hate from implied hate, two places where literal meaning and intended meaning come apart.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): LLM teacher tiers could return gated slot answers, such as "is there a speech act → which one", with explicit not_applicable values, so silver labels never contain contradictory parent and child labels.
- **I2** (frames): in crate prag, irony or offense judgments could run as a separate conditional pass only after the speech-act layer has fired, so that each decision stays isolated and explainable.
- **I3** (learn): teacher queries for VerbNet roles or frame labels could list the permitted inventory and use zero temperature, so silver data can be regenerated and checked against witness parsers.
- **I4** (learn): evaluation of LLM teacher tiers could use this three-way grid to decide whether a tier is worth fine-tuning or works well enough prompted.
- **I5** (frames): these make good test cases for the implicature and speech-act modules, for example a thanking act that should not by itself imply an affection state in the world of the text.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Chittagong University of Engineering & Technology](https://md.research.elamur.ai/free/en/universities/chittagong-university-of-engineering-technology/) — University, Chittagong, Bangladesh · 25 works · 29 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 972 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Ratnajit Dhar and Arpita Mallik. 2025. CUET-823 at MAHED 2025 Shared Task: Large Language Model-Based Framework for Emotion, Offensive, and Hate Detection in Arabic. Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{dhar2025cuet,
  title = {{CUET-823 at MAHED 2025 Shared Task: Large Language Model-Based Framework for Emotion, Offensive, and Hate Detection in Arabic}},
  author = {Ratnajit Dhar and Arpita Mallik},
  booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
  year = {2025},
  doi = {10.18653/v1/2025.arabicnlp-sharedtasks.84},
  url = {https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.84}
}
```

- [← previous Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding](https://md.research.elamur.ai/free/en/papers/al-homoud-2025-cross-lingual-synthdocs-large-scale/)
- [next → CUET-NLP_Team_SS306 at AraGenEval Shared Task: A Transformer-based Framework for Detecting AI-Generated Arabic Text](https://md.research.elamur.ai/free/en/papers/nath-2025-cuet-nlp-team-ss306-arageneval/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/14/)

## References

19 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Amr Al-Khatib and Samhaa R El-Beltagy. 2017. Emotional tone detection in arabic tweets. In International Conference on Computational Linguistics and Intelligent Text Processing, pages 105--114. Springer. [find](https://scholar.google.com/scholar?q=Amr+Al%2DKhatib+and+Samhaa+R+El%2DBeltagy%2E+2017%2E+Emotional+tone+detection+in+arabic+tweets%2E+In+International+Conference+on+Computational+Linguistics+and+Intelligent+Text+Processing%2C+pages+105%2D%2D114%2E+Spring)
2. Ali Al-Laith and Mamdouh Alenezi. 2021. Monitoring peoples emotions and symptoms from arabic tweets during the covid-19 pandemic. Information, 12(2):86. [↗](https://doi.org/10.3390/info12020086)
3. Sallam AL-Sarayreh, Azza Mohamed, and Khaled Shaalan. 2023. Challenges and solutions for arabic natural language processing in social media. In International conference on Variability of the Sun and sun-like stars: from asteroseismology to space weather, pages 293--302. Springer. [find](https://scholar.google.com/scholar?q=Sallam+AL%2DSarayreh%2C+Azza+Mohamed%2C+and+Khaled+Shaalan%2E+2023%2E+Challenges+and+solutions+for+arabic+natural+language+processing+in+social+media%2E+In+International+conference+on+Variability+of+the+Sun+and+s)
4. Zakaria H Ali and Hiba J Aleqabie. 2024. Emotion detection in arabic text in social media: A brief survey. Al-Furat Journal of Innovations in Electronics and Computer Engineering, 3(2):412--421. [find](https://scholar.google.com/scholar?q=Zakaria+H+Ali+and+Hiba+J+Aleqabie%2E+2024%2E+Emotion+detection+in+arabic+text+in+social+media%3A+A+brief+survey%2E+Al%2DFurat+Journal+of+Innovations+in+Electronics+and+Computer+Engineering%2C+3%282%29%3A412%2D%2D421%2E)
5. Ghadah Alqahtani and Abdulrahman Alothaim. 2022. Emotion analysis of arabic tweets: Language models and available resources. Frontiers in Artificial Intelligence, 5:843038. [↗](https://doi.org/10.3389/frai.2022.843038)
6. Center for Democracy and Technology. 2023. Moderating maghrebi arabic content on social media. [https://cdt.org/insights/moderat](https://cdt.org/insights/moderat) ing-maghrebi-arabic-content-on-socia l-media/. Accessed: 2025-08-03. [↗](https://cdt.org/insights/moderat)
7. Dieter Galea, Paolo Inglese, Lidia Cammack, Nicole Strittmatter, Monica Rebec, Reza Mirnezami, Ivan Laponogov, James Kinross, Jeremy Nicholson, Zoltan Takats, and 1 others. 2017. Translational utility of a hierarchical classification strategy in biomolecular data analytics. Scientific Reports, 7(1):14981. [find](https://scholar.google.com/scholar?q=Dieter+Galea%2C+Paolo+Inglese%2C+Lidia+Cammack%2C+Nicole+Strittmatter%2C+Monica+Rebec%2C+Reza+Mirnezami%2C+Ivan+Laponogov%2C+James+Kinross%2C+Jeremy+Nicholson%2C+Zoltan+Takats%2C+and+1+others%2E+2017%2E+Translational+utility)
8. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). arXiv preprint arXiv:2106.09685. [↗](https://arxiv.org/abs/2106.09685)
9. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2019%2E+Decoupled+weight+decay+regularization%2E+In+International+Conference+on+Learning+Representations%2E)
10. Khouloud Mnassri, Praboda Rajapaksha, Reza Farahbakhsh, and Noel Crespi. 2023. Hate speech and offensive language detection using an emotion-aware shared encoder. In ICC 2023-IEEE International Conference on Communications, pages 2852--2857. IEEE. [find](https://scholar.google.com/scholar?q=Khouloud+Mnassri%2C+Praboda+Rajapaksha%2C+Reza+Farahbakhsh%2C+and+Noel+Crespi%2E+2023%2E+Hate+speech+and+offensive+language+detection+using+an+emotion%2Daware+shared+encoder%2E+In+ICC+2023%2DIEEE+International+Confer)
11. Hamdy Mubarak, Ammar Rashed, Kareem Darwish, Younes Samih, and Ahmed Abdelali. 2020. [Arabic offensive language on twitter: Analysis and experiments](https://md.research.elamur.ai/free/en/papers/mubarak-2021-arabic-offensive-language-twitter-analysis/). arXiv preprint arXiv:2004.02192. [↗](https://arxiv.org/abs/2004.02192)
12. Abdelrahim Qaddoumi. 2022. Arabic sentiment ensemble nadi shared task 2. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP 2022). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Abdelrahim+Qaddoumi%2E+2022%2E+Arabic+sentiment+ensemble+nadi+shared+task+2%2E+In+Proceedings+of+the+Seventh+Arabic+Natural+Language+Processing+Workshop+%28WANLP+2022%29%2E+Association+for+Computational+Linguisti)
13. Omneya Rabie and Christian Sturm. 2014. Feel the heat: Emotion detection in arabic social media content. In The International Conference on Data Mining, Internet Computing, and Big Data (BigData2014), pages 37--49. Kuala Lumpur Citeseer. [find](https://scholar.google.com/scholar?q=Omneya+Rabie+and+Christian+Sturm%2E+2014%2E+Feel+the+heat%3A+Emotion+detection+in+arabic+social+media+content%2E+In+The+International+Conference+on+Data+Mining%2C+Internet+Computing%2C+and+Big+Data+%28BigData2014%29%2C)
14. Statista. United arab emirates: Number of internet users from 2010 to 2025. [https://www.statista.com/statistics/1389944/ua](https://www.statista.com/statistics/1389944/ua) e-number-of-internet-users/. Accessed: 2025-08-03. [↗](https://www.statista.com/statistics/1389944/ua)
15. Youpeng Yang, Qiuhong Zeng, Gaotong Liu, Shiyao Zheng, Tianyang Luo, Yibin Guo, Jia Tang, and Yi Huang. 2023. Hierarchical classification-based pan-cancer methylation analysis to classify primary cancer. BMC bioinformatics, 24(1):465. [↗](https://doi.org/10.1186/s12859-023-05529-0)
16. Wajdi Zaghouani and Md Rafiul Biswas. 2025a. [An annotated corpus of arabic tweets for hate speech analysis](https://md.research.elamur.ai/free/en/papers/zaghouani-2025-annotated-corpus-arabic-tweets-hate/). arXiv preprint arXiv:2505.11969. [↗](https://arxiv.org/abs/2505.11969)
17. Wajdi Zaghouani and Md Rafiul Biswas. 2025b. [Emohopespeech: An annotated dataset of emotions and hope speech in english and arabic](https://md.research.elamur.ai/free/en/papers/zaghouani-2025-emohopespeech-annotated-dataset-emotions-hope/). arXiv preprint arXiv:2505.11959. [↗](https://arxiv.org/abs/2505.11959)
18. Wajdi Zaghouani, Md Rafiul Biswas, Mabrouka Bessghaier, Shimaa Ibrahim, Georgios Mikros, Abul Hasnat, and Firoj Alam. 2025. [MAHED shared task: Multimodal detection of hope and hate emotions in arabic content](https://md.research.elamur.ai/free/en/papers/zaghouani-2025-mahed-shared-task-multimodal-detection/). In Proceedings of the Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics.
19. Wajdi Zaghouani, Hamdy Mubarak, and Md Rafiul Biswas. 2024. [So hateful! building a multi-label hate speech annotated arabic dataset](https://md.research.elamur.ai/free/en/papers/zaghouani-2024-so-hateful-building-multi-label/). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15044--15055.

*Updated 1 November 2026*