--- title: "Enhancing Medical Support in the Arabic Language Through Personalized ChatGPT Assistance — Issa 2024" description: "The work matters because Arabic medical support with LLMs is under-studied, and the paper offers a simple, repeatable way to evaluate it. 37 references." authors: ["Mohamed Issa", "Ahmed Abdelwahed"] year: 2024 venue: "arXiv:2403.15501" source: "https://arxiv.org/abs/2403.15501" doi: "10.48550/arxiv.2403.15501" arxiv: "2403.15501" licence: "CC BY 4.0 (arXiv)" licence_url: "http://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/issa-2024-enhancing-medical-support-arabic-language/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/issa-2024-enhancing-medical-support-arabic-language/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/6/) / Enhancing Medical Support in the Arabic Language Through Personalized ChatGPT Assistance # Enhancing Medical Support in the Arabic Language Through Personalized ChatGPT Assistance **Authors:** Mohamed Issa and Ahmed Abdelwahed · **Year:** 2024 · **Venue:** arXiv:2403.15501 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://arxiv.org/abs/2403.15501) · [PDF](https://arxiv.org/pdf/2403.15501) · [DOI 10.48550/arxiv.2403.15501](https://doi.org/10.48550/arxiv.2403.15501) · [arXiv 2403.15501](https://arxiv.org/abs/2403.15501) · [OpenAlex](https://openalex.org/W4393212283) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary The study asks whether ChatGPT can act as a free, real-time, personalized diagnostic helper for Arabic speakers. The authors position it as an alternative to clinic visits, paid telemedicine and rigid symptom checkers. They built a dataset of disease descriptions. From each disease they produced several Arabic patient-style messages, each written with a different prompting technique, and sent them to the ChatGPT API. To score the model, they compared each reply against the true disease using similarity measures, so no exact string match was needed. Across measures the average similarity came out at roughly 76%, and chain prompting did somewhat better than the other prompting styles. The authors also logged response time, which averaged 6.12 seconds per API call: workable, but worth improving. They conclude that ChatGPT cannot stand in for physicians but could help with emergencies and general medical questions. The work matters because Arabic medical support with LLMs is under-studied, and the paper offers a simple, repeatable way to evaluate it. ## Key points - The task is Arabic medical diagnosis with ChatGPT through its API, steered only by prompt engineering, with no fine-tuning. - The data is a compiled set of disease information, with multiple generated messages per disease, one for each prompting technique. The extracted text omits the methods section, so dataset size and the exact similarity metrics are not visible here. - The main result is an average similarity of about 76% between ChatGPT's answers and the reference diseases. - Chain prompting showed a relative advantage over the other prompting techniques. - The mean API latency was 6.12 s per response. - The intro lists the weaknesses of symptom checkers that motivate the work: low accuracy, fixed answer options, no use of patient history, and possible pharma bias. ## Interesting ideas - The test items are generated from a structured table: each disease record is turned into several free-text complaints in different styles, which checks robustness to phrasing rather than to one template, useful for any QA benchmark. - Free-form answers are graded by closeness to the gold label instead of exact match, which tolerates synonyms and paraphrased diagnoses. - Several prompting strategies are compared on identical items, and chain prompting (splitting the request into steps) wins, a cheap ablation that shows how to query a model. - Latency is reported next to quality, treating response time as a first-class metric for an interactive assistant. - Symptom checkers return a ranked list of likely diagnoses plus a triage level rather than one verdict, which communicates uncertainty and urgency separately. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (answer): Generate several differently worded questions from the same world facts in a tale or word problem. Then check that the reader returns the same answer for all of them. - **I2** (learn): A soft agreement score could grade LLM-teacher outputs against gold or silver labels. It should be paired with negative controls (unrelated labels) so that high similarity is not trivially reached. - **I3** (learn): When tiering LLM teachers for silver frames or trees, ask in staged steps (entities, then roles, then relation). Compare prompt variants on a fixed item set before trusting one. - **I4** (learn): The evaluation harness could record time per pipeline stage (tokens → tree → frames → world → answer). This would show where explainability costs speed. - **I5** (answer): Readers could output ranked candidate answers, each linked to its supporting world facts, plus a separate confidence or "needs more information" flag. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) Topics: [🐪 Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) ## Institutions - [Egypt-Japan University of Science and Technology](https://md.research.elamur.ai/free/en/universities/egypt-japan-university-of-science-and-technology/) — University, Alexandria, Egypt · 2 works · 1 citation - [Zagazig University](https://md.research.elamur.ai/free/en/universities/zagazig-university/) — University, Zagazig, Egypt · 2 works · 1 citation ## Cite Cite as: Mohamed Issa and Ahmed Abdelwahed. 2024. Enhancing Medical Support in the Arabic Language Through Personalized ChatGPT Assistance. arXiv:2403.15501. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{issa2024enhancing, title = {{Enhancing Medical Support in the Arabic Language Through Personalized ChatGPT Assistance}}, author = {Mohamed Issa and Ahmed Abdelwahed}, year = {2024}, doi = {10.48550/arxiv.2403.15501}, eprint = {2403.15501}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.2403.15501} } ``` - [← previous Dynamic changes in search strategy during chain-of-thought reasoning of language models](https://md.research.elamur.ai/free/en/papers/aoki-2024-dynamic-changes-search-strategy/) - [next → Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets](https://md.research.elamur.ai/free/en/papers/keleg-2024-estimating-level-dialectness-predicts-interannotator/) - [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/6/) ## References 37 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Gann, B. "Giving patients choice and control: health informatics on the patient journey." Yearbook of medical informatics 21, no. 01 (2012): 70-73. [find](https://scholar.google.com/scholar?q=Gann%2C+B%2E+%22Giving+patients+choice+and+control%3A+health+informatics+on+the+patient+journey%2E%22+Yearbook+of+medical+informatics+21%2C+no%2E+01+%282012%29%3A+70%2D73%2E) 2. North, Frederick, William J. Ward, Prathibha Varkey, and Sidna M. TulledgeScheitel. "Should you search the Internet for information about your acute symptom?." Telemedicine and e-Health 18, no. 3 (2012): 213-218. [find](https://scholar.google.com/scholar?q=North%2C+Frederick%2C+William+J%2E+Ward%2C+Prathibha+Varkey%2C+and+Sidna+M%2E+TulledgeScheitel%2E+%22Should+you+search+the+Internet+for+information+about+your+acute+symptom%3F%2E%22+Telemedicine+and+e%2DHealth+18%2C+no%2E+3+%28201) 3. Chen, Zhongbo, and Martin R. Turner. "The internet for self-diagnosis and prognostication in ALS." Amyotrophic Lateral Sclerosis 11, no. 6 (2010): 565-567. [find](https://scholar.google.com/scholar?q=Chen%2C+Zhongbo%2C+and+Martin+R%2E+Turner%2E+%22The+internet+for+self%2Ddiagnosis+and+prognostication+in+ALS%2E%22+Amyotrophic+Lateral+Sclerosis+11%2C+no%2E+6+%282010%29%3A+565%2D567%2E) 4. North, Frederick, Prathibha Varkey, Brian Laing, Steven S. Cha, and Sidna TulledgeScheitel. "Are e-health web users looking for different symptom information than callers to triage centers?." Telemedicine and e-Health 17, no. 1 (2011): 19-24. [find](https://scholar.google.com/scholar?q=North%2C+Frederick%2C+Prathibha+Varkey%2C+Brian+Laing%2C+Steven+S%2E+Cha%2C+and+Sidna+TulledgeScheitel%2E+%22Are+e%2Dhealth+web+users+looking+for+different+symptom+information+than+callers+to+triage+centers%3F%2E%22+Telemedi) 5. Nakagawa, Keisuke, Joseph Kvedar, and Peter Yellowlees. "Retail outlets using telehealth pose significant policy questions for health care." Health Affairs 37, no. 12 (2018): 2069-2075. [find](https://scholar.google.com/scholar?q=Nakagawa%2C+Keisuke%2C+Joseph+Kvedar%2C+and+Peter+Yellowlees%2E+%22Retail+outlets+using+telehealth+pose+significant+policy+questions+for+health+care%2E%22+Health+Affairs+37%2C+no%2E+12+%282018%29%3A+2069%2D2075%2E) 6. Saczynski, Jane S., Jorge Yarzebski, Darleen Lessard, Frederick A. Spencer, Jerry H. Gurwitz, Joel M. Gore, and Robert J. Goldberg. "Trends in prehospital delay in patients with acute myocardial infarction (from the Worcester Heart Attack Study)." The American journal of cardiology 102, no. 12 (2008): 1589-1594. [find](https://scholar.google.com/scholar?q=Saczynski%2C+Jane+S%2E%2C+Jorge+Yarzebski%2C+Darleen+Lessard%2C+Frederick+A%2E+Spencer%2C+Jerry+H%2E+Gurwitz%2C+Joel+M%2E+Gore%2C+and+Robert+J%2E+Goldberg%2E+%22Trends+in+prehospital+delay+in+patients+with+acute+myocardial+infar) 7. Barnett, Michael L., and Jeffrey A. Linder. "Antibiotic prescribing to adults with sore throat in the United States, 1997-2010." JAMA internal medicine 174, no. 1 (2014): 138-140. [find](https://scholar.google.com/scholar?q=Barnett%2C+Michael+L%2E%2C+and+Jeffrey+A%2E+Linder%2E+%22Antibiotic+prescribing+to+adults+with+sore+throat+in+the+United+States%2C+1997%2D2010%2E%22+JAMA+internal+medicine+174%2C+no%2E+1+%282014%29%3A+138%2D140%2E) 8. Gunawan, Joko. "Exploring the future of nursing: Insights from the ChatGPT model." Belitung Nursing Journal 9, no. 1 (2023): 1-5. [find](https://scholar.google.com/scholar?q=Gunawan%2C+Joko%2E+%22Exploring+the+future+of+nursing%3A+Insights+from+the+ChatGPT+model%2E%22+Belitung+Nursing+Journal+9%2C+no%2E+1+%282023%29%3A+1%2D5%2E) 9. Biswas, Som. "ChatGPT and the future of medical writing." Radiology 307, no. 2 (2023): e223312. [find](https://scholar.google.com/scholar?q=Biswas%2C+Som%2E+%22ChatGPT+and+the+future+of+medical+writing%2E%22+Radiology+307%2C+no%2E+2+%282023%29%3A+e223312%2E) 10. Alhasan, Khalid, Jaffar Al-Tawfiq, Fadi Aljamaan, Amr Jamal, Ayman Al-Eyadhy, Mohamad-Hani Temsah, and Jaffar A. Al-Tawfiq. "Mitigating the burden of severe pediatric respiratory viruses in the post-COVID-19 era: ChatGPT insights and recommendations." Cureus 15, no. 3 (2023). [find](https://scholar.google.com/scholar?q=Alhasan%2C+Khalid%2C+Jaffar+Al%2DTawfiq%2C+Fadi+Aljamaan%2C+Amr+Jamal%2C+Ayman+Al%2DEyadhy%2C+Mohamad%2DHani+Temsah%2C+and+Jaffar+A%2E+Al%2DTawfiq%2E+%22Mitigating+the+burden+of+severe+pediatric+respiratory+viruses+in+the+post%2DC) 11. De Angelis, Luigi, Francesco Baglivo, Guglielmo Arzilli, Gaetano Pierpaolo Privitera, Paolo Ferragina, Alberto Eugenio Tozzi, and Caterina Rizzo. "ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health." Frontiers in Public Health 11 (2023): 1166120. [find](https://scholar.google.com/scholar?q=De+Angelis%2C+Luigi%2C+Francesco+Baglivo%2C+Guglielmo+Arzilli%2C+Gaetano+Pierpaolo+Privitera%2C+Paolo+Ferragina%2C+Alberto+Eugenio+Tozzi%2C+and+Caterina+Rizzo%2E+%22ChatGPT+and+the+rise+of+large+language+models%3A+the+ne) 12. Mbakwe, Amarachi B., Ismini Lourentzou, Leo Anthony Celi, Oren J. Mechanic, and Alon Dagan. "ChatGPT passing USMLE shines a spotlight on the flaws of medical education." PLOS Digital Health 2, no. 2 (2023): e0000205. [find](https://scholar.google.com/scholar?q=Mbakwe%2C+Amarachi+B%2E%2C+Ismini+Lourentzou%2C+Leo+Anthony+Celi%2C+Oren+J%2E+Mechanic%2C+and+Alon+Dagan%2E+%22ChatGPT+passing+USMLE+shines+a+spotlight+on+the+flaws+of+medical+education%2E%22+PLOS+Digital+Health+2%2C+no%2E+2+%28) 13. Homolak, Jan. "Opportunities and risks of ChatGPT in medicine, science, and academic publishing: a modern Promethean dilemma." Croatian Medical Journal 64, no. 1 (2023): 1. [find](https://scholar.google.com/scholar?q=Homolak%2C+Jan%2E+%22Opportunities+and+risks+of+ChatGPT+in+medicine%2C+science%2C+and+academic+publishing%3A+a+modern+Promethean+dilemma%2E%22+Croatian+Medical+Journal+64%2C+no%2E+1+%282023%29%3A+1%2E) 14. Mann, Douglas L. "Artificial intelligence discusses the role of artificial intelligence in translational medicine: a JACC: basic to translational science interview with ChatGPT." Basic to Translational Science 8, no. 2 (2023): 221- 223. [find](https://scholar.google.com/scholar?q=Mann%2C+Douglas+L%2E+%22Artificial+intelligence+discusses+the+role+of+artificial+intelligence+in+translational+medicine%3A+a+JACC%3A+basic+to+translational+science+interview+with+ChatGPT%2E%22+Basic+to+Translationa) 15. Arif, Taha Bin, Uzair Munaf, and Ibtehaj Ul-Haque. "The future of medical education and research: Is ChatGPT a blessing or blight in disguise?." Medical education online 28, no. 1 (2023): 2181052. [find](https://scholar.google.com/scholar?q=Arif%2C+Taha+Bin%2C+Uzair+Munaf%2C+and+Ibtehaj+Ul%2DHaque%2E+%22The+future+of+medical+education+and+research%3A+Is+ChatGPT+a+blessing+or+blight+in+disguise%3F%2E%22+Medical+education+online+28%2C+no%2E+1+%282023%29%3A+2181052%2E) 16. Hosseini, Mohammad, and Serge PJM Horbach. "Fighting reviewer fatigue or amplifying bias? Considerations and recommendations for use of ChatGPT and other Large Language Models in scholarly peer review." Research Integrity and Peer Review 8, no. 1 (2023): 4. [find](https://scholar.google.com/scholar?q=Hosseini%2C+Mohammad%2C+and+Serge+PJM+Horbach%2E+%22Fighting+reviewer+fatigue+or+amplifying+bias%3F+Considerations+and+recommendations+for+use+of+ChatGPT+and+other+Large+Language+Models+in+scholarly+peer+review) 17. Aydın, Ömer, and Enis Karaarslan. "OpenAI ChatGPT generated literature review: Digital twin in healthcare." Available at SSRN 4308687 (2022). [find](https://scholar.google.com/scholar?q=Ayd%C4%B1n%2C+%C3%96mer%2C+and+Enis+Karaarslan%2E+%22OpenAI+ChatGPT+generated+literature+review%3A+Digital+twin+in+healthcare%2E%22+Available+at+SSRN+4308687+%282022%29%2E) 18. Cascella, Marco, Jonathan Montomoli, Valentina Bellini, and Elena Bignami. "Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios." Journal of Medical Systems 47, no. 1 (2023): 33. [find](https://scholar.google.com/scholar?q=Cascella%2C+Marco%2C+Jonathan+Montomoli%2C+Valentina+Bellini%2C+and+Elena+Bignami%2E+%22Evaluating+the+feasibility+of+ChatGPT+in+healthcare%3A+an+analysis+of+multiple+clinical+and+research+scenarios%2E%22+Journal+of+Me) 19. Javaid, Mohd, Abid Haleem, and Ravi Pratap Singh. "ChatGPT for healthcare services: An emerging stage for an innovative perspective." BenchCouncil Transactions on Benchmarks, Standards and Evaluations 3, no. 1 (2023): 100105. [find](https://scholar.google.com/scholar?q=Javaid%2C+Mohd%2C+Abid+Haleem%2C+and+Ravi+Pratap+Singh%2E+%22ChatGPT+for+healthcare+services%3A+An+emerging+stage+for+an+innovative+perspective%2E%22+BenchCouncil+Transactions+on+Benchmarks%2C+Standards+and+Evaluations) 20. Li, Jianning, Amin Dada, Jens Kleesiek, and Jan Egger. "ChatGPT in Healthcare: A Taxonomy and Systematic Review." medRxiv (2023): 2023-03. [find](https://scholar.google.com/scholar?q=Li%2C+Jianning%2C+Amin+Dada%2C+Jens+Kleesiek%2C+and+Jan+Egger%2E+%22ChatGPT+in+Healthcare%3A+A+Taxonomy+and+Systematic+Review%2E%22+medRxiv+%282023%29%3A+2023%2D03%2E) 21. Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. "Attention is all you need." Advances in neural information processing systems 30 (2017). [our card](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/) 22. Christiano, Paul F., Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. "Deep reinforcement learning from human preferences." Advances in neural information processing systems 30 (2017). [find](https://scholar.google.com/scholar?q=Christiano%2C+Paul+F%2E%2C+Jan+Leike%2C+Tom+Brown%2C+Miljan+Martic%2C+Shane+Legg%2C+and+Dario+Amodei%2E+%22Deep+reinforcement+learning+from+human+preferences%2E%22+Advances+in+neural+information+processing+systems+30+%282017) 23. Taecharungroj, Viriya. "“What Can ChatGPT Do?” Analyzing Early Reactions to the Innovative AI Chatbot on Twitter." Big Data and Cognitive Computing 7, no. 1 (2023): 35. [find](https://scholar.google.com/scholar?q=Taecharungroj%2C+Viriya%2E+%22%E2%80%9CWhat+Can+ChatGPT+Do%3F%E2%80%9D+Analyzing+Early+Reactions+to+the+Innovative+AI+Chatbot+on+Twitter%2E%22+Big+Data+and+Cognitive+Computing+7%2C+no%2E+1+%282023%29%3A+35%2E) 24. Kung, Tiffany H., Morgan Cheatham, Arielle Medenilla, Czarina Sillos, Lorie De Leon, Camille Elepaño, Maria Madriaga et al. "Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models." PLoS digital health 2, no. 2 (2023): e0000198. [our card](https://md.research.elamur.ai/free/en/papers/kung-2023-performance-chatgpt-usmle-potential-ai/) 25. Muftić, Fatima, Merjem Kadunić, Almina Mušinbegović, and Ali Abd Almisreb. "Exploring Medical Breakthroughs: A Systematic Review of ChatGPT Applications in Healthcare." Southeast Europe Journal of Soft Computing 12, no. 1 (2023): 13-41. [find](https://scholar.google.com/scholar?q=Mufti%C4%87%2C+Fatima%2C+Merjem+Kaduni%C4%87%2C+Almina+Mu%C5%A1inbegovi%C4%87%2C+and+Ali+Abd+Almisreb%2E+%22Exploring+Medical+Breakthroughs%3A+A+Systematic+Review+of+ChatGPT+Applications+in+Healthcare%2E%22+Southeast+Europe+Journal+of+Sof) 26. Temsah, Mohamad-Hani, Amr Jamal, and Jaffar A. Al-Tawfiq. "Reflection with ChatGPT about the excess death after the COVID-19 pandemic." New Microbes and New Infections (2023). [find](https://scholar.google.com/scholar?q=Temsah%2C+Mohamad%2DHani%2C+Amr+Jamal%2C+and+Jaffar+A%2E+Al%2DTawfiq%2E+%22Reflection+with+ChatGPT+about+the+excess+death+after+the+COVID%2D19+pandemic%2E%22+New+Microbes+and+New+Infections+%282023%29%2E) 27. Shen, Yiqiu, Laura Heacock, Jonathan Elias, Keith D. Hentel, Beatriu Reig, George Shih, and Linda Moy. "ChatGPT and other large language models are double-edged swords." Radiology 307, no. 2 (2023): e230163. [find](https://scholar.google.com/scholar?q=Shen%2C+Yiqiu%2C+Laura+Heacock%2C+Jonathan+Elias%2C+Keith+D%2E+Hentel%2C+Beatriu+Reig%2C+George+Shih%2C+and+Linda+Moy%2E+%22ChatGPT+and+other+large+language+models+are+double%2Dedged+swords%2E%22+Radiology+307%2C+no%2E+2+%282023%29%3A+e) 28. DiGiorgio, Anthony M., and Jesse M. Ehrenfeld. "Artificial intelligence in medicine & ChatGPT: de-tether the physician." Journal of Medical Systems 47, no. 1 (2023): 32. [find](https://scholar.google.com/scholar?q=DiGiorgio%2C+Anthony+M%2E%2C+and+Jesse+M%2E+Ehrenfeld%2E+%22Artificial+intelligence+in+medicine+%26+ChatGPT%3A+de%2Dtether+the+physician%2E%22+Journal+of+Medical+Systems+47%2C+no%2E+1+%282023%29%3A+32%2E) 29. Johnson, Skyler B., Andy J. King, Echo L. Warner, Sanjay Aneja, Benjamin H. Kann, and Carma L. Bylund. "Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information." JNCI cancer spectrum 7, no. 2 (2023): pkad015. [find](https://scholar.google.com/scholar?q=Johnson%2C+Skyler+B%2E%2C+Andy+J%2E+King%2C+Echo+L%2E+Warner%2C+Sanjay+Aneja%2C+Benjamin+H%2E+Kann%2C+and+Carma+L%2E+Bylund%2E+%22Using+ChatGPT+to+evaluate+cancer+myths+and+misconceptions%3A+artificial+intelligence+and+cancer+in) 30. Grünebaum, Amos, Joseph Chervenak, Susan L. Pollet, Adi Katz, and Frank A. Chervenak. "The exciting potential for ChatGPT in obstetrics and gynecology." American Journal of Obstetrics and Gynecology 228, no. 6 (2023): 696-705. [find](https://scholar.google.com/scholar?q=Gr%C3%BCnebaum%2C+Amos%2C+Joseph+Chervenak%2C+Susan+L%2E+Pollet%2C+Adi+Katz%2C+and+Frank+A%2E+Chervenak%2E+%22The+exciting+potential+for+ChatGPT+in+obstetrics+and+gynecology%2E%22+American+Journal+of+Obstetrics+and+Gynecology+2) 31. Abdullah, Malak, Alia Madain, and Yaser Jararweh. "ChatGPT: Fundamentals, applications and social impacts." In 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS), pp. 1-8. IEEE, 2022. [find](https://scholar.google.com/scholar?q=Abdullah%2C+Malak%2C+Alia+Madain%2C+and+Yaser+Jararweh%2E+%22ChatGPT%3A+Fundamentals%2C+applications+and+social+impacts%2E%22+In+2022+Ninth+International+Conference+on+Social+Networks+Analysis%2C+Management+and+Security+) 32. White, Jules, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C. Schmidt. "A prompt pattern catalog to enhance prompt engineering with chatgpt." arXiv preprint arXiv:2302.11382 (2023). [↗](https://arxiv.org/abs/2302.11382) [our card](https://md.research.elamur.ai/free/en/papers/white-2023-prompt-pattern-catalog-enhance-prompt/) 33. Sorin, Vera, Yiftach Barash, Eli Konen, and Eyal Klang. "Deep-learning natural language processing for oncological applications." The Lancet Oncology 21, no. 12 (2020): 1553-1556. [find](https://scholar.google.com/scholar?q=Sorin%2C+Vera%2C+Yiftach+Barash%2C+Eli+Konen%2C+and+Eyal+Klang%2E+%22Deep%2Dlearning+natural+language+processing+for+oncological+applications%2E%22+The+Lancet+Oncology+21%2C+no%2E+12+%282020%29%3A+1553%2D1556%2E) 34. Short, Cole E., and Jeremy C. Short. "The artificially intelligent entrepreneur: ChatGPT, prompt engineering, and entrepreneurial rhetoric creation." Journal of Business Venturing Insights 19 (2023): e00388. [find](https://scholar.google.com/scholar?q=Short%2C+Cole+E%2E%2C+and+Jeremy+C%2E+Short%2E+%22The+artificially+intelligent+entrepreneur%3A+ChatGPT%2C+prompt+engineering%2C+and+entrepreneurial+rhetoric+creation%2E%22+Journal+of+Business+Venturing+Insights+19+%282023%29%3A+) 35. Chen, Jiuhai, Lichang Chen, Heng Huang, and Tianyi Zhou. "When do you need Chain-of-Thought Prompting for ChatGPT?." arXiv preprint arXiv:2304.03262 (2023) [↗](https://arxiv.org/abs/2304.03262) 36. Berjon, Robin. "The fiduciary duties of user agents." Available at SSRN 3827421 (2021). [find](https://scholar.google.com/scholar?q=Berjon%2C+Robin%2E+%22The+fiduciary+duties+of+user+agents%2E%22+Available+at+SSRN+3827421+%282021%29%2E) 37. Wang, Liang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. "Text embeddings by weakly-supervised contrastive pre-training." arXiv preprint arXiv:2212.03533 (2022). [↗](https://arxiv.org/abs/2212.03533) [our card](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/)