---
title: "mucAI at AraHealthQA 2025 — paper by Abdou (2025)"
description: "The author proposes ERV (Explain–Retrieve–Verify), a training-free workflow built in DSPy on… 0.61 F1. 15 references, cited by 1 paper here."
authors: ["Ahmed Abdou"]
year: 2025
venue: "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks"
source: "https://aclanthology.org/2025.arabicnlp-sharedtasks.32/"
doi: "10.18653/v1/2025.arabicnlp-sharedtasks.32"
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/abdou-2025-mucai-arahealthqa-2025-explain-retrieve/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/abdou-2025-mucai-arahealthqa-2025-explain-retrieve/)

[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/16/) / mucAI at AraHealthQA 2025: Explain–Retrieve–Verify (ERV) Workflow for Multi-Label Arabic Health QA Classification

# mucAI at AraHealthQA 2025: Explain–Retrieve–Verify (ERV) Workflow for Multi-Label Arabic Health QA Classification

**Authors:** [Ahmed Abdou](https://md.research.elamur.ai/free/en/authors/ahmed-abdou/) · **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.32/) · [PDF](https://aclanthology.org/2025.arabicnlp-sharedtasks.32.pdf) · [DOI 10.18653/v1/2025.arabicnlp-sharedtasks.32](https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.32) · [OpenAlex](https://openalex.org/W4416037805)

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

## Summary
The paper addresses multi-label classification for Track 1 of AraHealthQA 2025 (MentalQA). The task has two parts: tagging Arabic mental-health questions with seven question types, and tagging doctors' answers with three communication strategies. The data is the MentalQA dataset, 500 question–answer pairs from Altibbi.com, split 300/50/150. The author proposes ERV (Explain–Retrieve–Verify), a training-free workflow built in DSPy on top of GPT-4. It runs in three steps:

1. The LLM reasons step by step and proposes labels, a rationale and a self-confidence score.
2. The system fetches the most similar training items using a multilingual Sentence-BERT model, and an LLM infers likely labels from their gold tags.
3. A verifier LLM weighs both sources against the full taxonomy and outputs the final labels, a confidence score and a short note explaining how conflicts were settled.

For questions, ERV beats fine-tuned MARBERT and AraBERT (weighted F1 0.61 vs 0.56). For answers it trails them (0.73 vs 0.76). A hybrid that hands only the Emotional Support label to ERV reaches 0.80. The work shows that retrieval-backed LLM reasoning can recover rare classes that small-data fine-tuning ignores, and it leaves a human-readable decision trail.

## Key points
- **Dataset:** MentalQA, built from Altibbi.com posts from 2020–2021.
  - Question labels: seven categories, namely Diagnosis (A), Treatment (B), Anatomy & Physiology (C), Epidemiology (D), Healthy Lifestyle (E), Provider Choice (F) and Other (Z).
  - Answer labels: 1 Information, 2 Direct Guidance, 3 Emotional Support.
  - Metrics: weighted F1 and instance-based Jaccard.
- **Setup:**
  - ERV uses GPT-4, embeddings from paraphrase-multilingual-mpnet-base-v2, and cosine kNN over cached training embeddings.
  - Baselines are MARBERT and AraBERT-v02, fine-tuned with lr 2×10⁻⁵, batch 16, 5 epochs and weight decay 0.01.
- **Question results (test):** ERV scores 0.61 F1 / 0.53 Jaccard; both baselines score 0.56 / 0.51.
- **Answer results (test):**

  | System | F1 | Jaccard |
  |---|---|---|
  | MARBERT | 0.76 | 0.73 |
  | AraBERT | 0.74 | 0.68 |
  | ERV | 0.73 | 0.61 |
  | MARBERT+ERV hybrid | 0.80 | 0.72 |

- **Per-label findings:**
  - MARBERT scores zero F1 on C, F and Emotional Support. ERV reaches 0.20, 0.15 and 0.44 on these.
  - ERV leans toward recall, for example 0.99 recall on Direct Guidance.
  - The main cost is three sequential LLM calls per item.

## Interesting ideas
- Two independent evidence channels (the model's own reasoning and the gold labels of nearest training cases) are merged by a verifier that must write down how it resolved each disagreement, so the decision stays auditable.
- The hybrid routes labels rather than averaging models: the strong classifier keeps the majority labels, and a different system takes over only the label where the main one scores zero.
- Nearest labelled neighbours act as case-based priors that rescue minority classes in tiny datasets, and the author suggests interpolating a fine-tuned model with kNN at inference.
- A per-class precision/recall breakdown exposed labels with zero F1 that the weighted averages hid, which changed the system design.

## For Mova

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

- **I1** (frames): role or speech-act assignment could run a rule-based reading and a nearest-annotated-example reading separately, with a reconciler logging why one reading won.
- **I2** (answer): question types on which the main reader systematically fails could be routed to a dedicated fallback reader, keeping each path's reasoning visible.
- **I3** (tree): the perceptron parser could be blended with kNN over treebank contexts to improve rare deprels where training counts are too small.
- **I4** (learn): evaluation reports should always list per-label scores and flag any zero-F1 class before trusting an aggregate number.

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

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 330 works

🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 487 works

## Cite

Cite as: Ahmed Abdou. 2025. mucAI at AraHealthQA 2025: Explain–Retrieve–Verify (ERV) Workflow for Multi-Label Arabic Health QA Classification. 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{abdou2025mucai,
  title = {{mucAI at AraHealthQA 2025: Explain–Retrieve–Verify (ERV) Workflow for Multi-Label Arabic Health QA Classification}},
  author = {Ahmed Abdou},
  booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
  year = {2025},
  doi = {10.18653/v1/2025.arabicnlp-sharedtasks.32},
  url = {https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.32}
}
```

- [← previous MorphoArabia at BAREC Shared Task 2025: A Hybrid Architecture with Morphological Analysis for Arabic Readability Assessment](https://md.research.elamur.ai/free/en/papers/elden-2025-morphoarabia-barec-shared-task-2025/)
- [next → mucAI at BAREC Shared Task 2025: Towards Uncertainty Aware Arabic Readability Assessment](https://md.research.elamur.ai/free/en/papers/abdou-2025-mucai-barec-shared-task-2025/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/16/)

## References

15 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Muhammad Abdul-Mageed, AbdelRahim Elmadany, and El Moatez Billah Nagoudi. 2020. [Arbert & marbert: Deep bidirectional transformers for arabic](https://md.research.elamur.ai/free/en/papers/abdul-mageed-2021-arbert-marbert-deep-bidirectional-transformers/). arXiv preprint arXiv:2101.01785. [↗](https://arxiv.org/abs/2101.01785)
2. Mouath Abu Daoud, Chaimae Abouzahir, Leen Kharouf, Walid Al-Eisawi, Nizar Habash, and Farah E Shamout. 2025. [Medarabiq: Benchmarking large language models on arabic medical tasks](https://md.research.elamur.ai/free/en/papers/daoud-2025-medarabiq-benchmarking-large-language-models/). arXiv e-prints, pages arXiv–2505.
3. Hassan Alhuzali, Ashwag Alasmari, and Hamad Al-saleh. 2024. Mentalqa: An annotated arabic corpus for questions and answers of mental healthcare. IEEE Access. [↗](https://doi.org/10.1109/access.2024.3430068)
4. Hassan Alhuzali, Farah Shamout, Muhammad Abdul-Mageed, Chaimae Abouzahir, Mouath Abu-Daoud, Ashwag Alasmari, Walid Al-Eisawi, Renad Al-Monef, Ali Alqahtani, Lama Ayash, Nizar Habash, and Leen Kharouf. 2025. Arahealthqa 2025 shared task description paper. In Proceedings of ArabicNLP 2025. [find](https://scholar.google.com/scholar?q=Hassan+Alhuzali%2C+Farah+Shamout%2C+Muhammad+Abdul%2DMageed%2C+Chaimae+Abouzahir%2C+Mouath+Abu%2DDaoud%2C+Ashwag+Alasmari%2C+Walid+Al%2DEisawi%2C+Renad+Al%2DMonef%2C+Ali+Alqahtani%2C+Lama+Ayash%2C+Nizar+Habash%2C+and+Leen+Kharouf%2E)
5. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. [AraBERT: Transformer-based model for Arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/). In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resource Association. [↗](https://doi.org/10.48550/arxiv.2003.00104)
6. Akshay Swaminathan, Iván López, Rafael Antonio Garcia Mar, Tyler Heist, Tom McClintock, Kaitlin Caoili, Madeline Grace, Matthew Rubashkin, Michael N Boggs, Jonathan H Chen, and 1 others. 2023. Natural language processing system for rapid detection and intervention of mental health crisis chat messages. NPJ digital medicine, 6(1):213. [find](https://scholar.google.com/scholar?q=Akshay+Swaminathan%2C+Iv%C3%A1n+L%C3%B3pez%2C+Rafael+Antonio+Garcia+Mar%2C+Tyler+Heist%2C+Tom+McClintock%2C+Kaitlin+Caoili%2C+Madeline+Grace%2C+Matthew+Rubashkin%2C+Michael+N+Boggs%2C+Jonathan+H+Chen%2C+and+1+others%2E+2023%2E+Natural)
7. Qianqian Xie, Qingyu Chen, Aokun Chen, Cheng Peng, Yan Hu, Fongci Lin, Xueqing Peng, Jimin Huang, Jeffrey Zhang, Vipina Keloth, and 1 others. 2025. Medical foundation large language models for comprehensive text analysis and beyond. npj Digital Medicine, 8(1):141. [find](https://scholar.google.com/scholar?q=Qianqian+Xie%2C+Qingyu+Chen%2C+Aokun+Chen%2C+Cheng+Peng%2C+Yan+Hu%2C+Fongci+Lin%2C+Xueqing+Peng%2C+Jimin+Huang%2C+Jeffrey+Zhang%2C+Vipina+Keloth%2C+and+1+others%2E+2025%2E+Medical+foundation+large+language+models+for+compreh)
8. Kailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie, Ziyan Kuang, and Sophia Ananiadou. 2023. Towards interpretable mental health analysis with large language models. arXiv preprint arXiv:2304.03347. [↗](https://arxiv.org/abs/2304.03347)
9. Monica Zolezzi, Maha Alamri, Shahd Shaar, and Daniel Rainkie. 2018. Stigma associated with mental illness and its treatment in the arab culture: a systematic review. International Journal of Social Psychiatry, 64(6):597–609. [↗](https://doi.org/10.1177/0020764018789200)
10. A Thushari Atapattu, Mahen Herath, Charitha Elvitigala, Piyanjali de Zoysa, Kasun Gunawardana, Menasha Thilakaratne, Kasun De Zoysa, and Katrina Falkner. 2022. Emoment: An emotion annotated mental health corpus from two south asian countries. arXiv preprint arXiv:2208.08486. [↗](https://arxiv.org/abs/2208.08486)
11. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
12. Jaya Chaturvedi, Sumithra Velupillai, Robert Stewart, and Angus Roberts. 2023. Identifying mentions of pain in mental health records text: a natural language processing approach. arXiv preprint arXiv:2304.01240. [↗](https://arxiv.org/abs/2304.01240)
13. Soumitra Ghosh, Asif Ekbal, and Pushpak Bhattacharyya. 2020. [Cease, a corpus of emotion annotated suicide notes in english](https://md.research.elamur.ai/free/en/papers/ghosh-2020-cease-corpus-emotion-annotated-suicide/). In Proceedings of the twelfth language resources and evaluation conference, pages 1618–1626.
14. Imane Guellil, Houda Saâdane, Faical Azouaou, Billel Gueni, and Damien Nouvel. 2021. [Arabic natural language processing: An overview](https://md.research.elamur.ai/free/en/papers/guellil-2019-arabic-natural-language-processing-overview/). Journal of King Saud University-Computer and Information Sciences, 33(5):497–507.
15. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.

*Updated 1 November 2026*