About me
Final-year PhD student in Computer Science, Natural Language Processing (NLP) at the University of Sheffield. I started at the Speech and Language Technology (SLT) Centre for Doctoral training (CDT) in September 2021. My focus lies in numerical reasoning especially how to evaluate and improve smaller accessible general-prupose model to enhance their numerical understanding in downstream tasks. As part of my internship at both Amazon and Huawei, I have expanded my interest to multilingualism and multiculturalism especially for low-resource languages, formal language specifically for automatic theorem proving. At the University of Sheffield, I have also done some consulting to introduce speech and language AI features for marketing, teaching and robotics. My background is in mathematics and previously I was a mathematics teacher in a secondary school. I also taught French and English in Colombia.
News
- May 26 - Invited Talk: Delivered talk on "Beneath the surface of LLMs" at the Universidad de Rio do Sul.
- Nov 25 - Invited Talk: Presented "Conjecturing" at the Amazon Formal Language Seminar.
- Oct 25 - Invited Talk: Delivered talk on "Beneath the surface of LLMs" at the Università di Napoli L'Orientale.
- Oct 25 - Invited Talk: Presented "Conjecturing" at the Sheffield NLP Seminar.
- Dec 24 - Invited Talk: Spoke on "Numerical Reasoning" at Huawei Noah's Ark Lab (NLP).
- Nov 24 - Invited Talk: Presented a high-level functioning of LLMs in Chatbot to undergraduate law students.
- Jan 24 - Emergency Reviewer: Reviewed for LREC-Coling 2024, tracks "Less-Resourced/Endangered/Less-studied Languages" and "Social Media Processing".
- Nov 23 - Huggingface Workshop: Delivered first workshop to undergraduates explaining how to train a model on custom dataset using huggingface.
- Nov 23 - Supervision: Started jointly supervising two undergraduate students on multilingual numerical reasoning and number decoding.
- Jul 23 - Youtube fame: Feature in AI Coffee Break youtube channel in ACL video at 8 mins 51 at ACL main conference, Toronto, Canada.
- Jul 23 - Conference: Attended ACL 2023 in Toronto where I also presented FERMAT at the main conference.
- Jun 23 - Quizmaster: Entertained the attendees of UKSpeech 2023 at their social event with a quiz.
- Jun 23 - Invited talk: Presented FERMAT at the third annual Center for Doctoral Training in Speech and Language Technologies in Sheffield, UK.
- May 23 - Field trip: Travelled to San Basilio de Palenque, Colombia to meet the afro-colombian Palenquero people and collect their native language data.
- Feb 23 - Examiner: Marked third year undergraduate scripts for Professional Issues course.
- Jun 22 - Conference Organiser: Student organiser of panel discussion at the Sheffield CDT second annual conferrence.
Publications
- Pastorino, V., Sivakumar, J. & Moosavi, N. (2026). Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection In Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC), Palma de Mallorca, Spain. European Language Resources Association.
- Paul, D., Murphy, D., et. al. including Sivakumar, J. (2026). A Benchmark for Deep Information Synthesis In International Conference on Learning Representations (ICLR).
- Sivakumar, J. , Borchert, P., Cardenas, R. & Lampouras, G. (2025). Conjecturing: An Overlooked Step in Formal Mathematical Reasoning Arxiv Preprint.
- Sivakumar, J. , & Moosavi, N. (2025). How to Leverage Digit Embeddings to Represent Numbers? Proceedings of the 31st International Conference on Computational Linguistics (Volume 1: Long Papers). Conference on Computational Linguistics. (COLING)
- Sivakumar, J. , & Moosavi, N. (2023). FERMAT: An Alternative to Accuracy for Numerical Reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 15026–15043). Association for Computational Linguistics. (ACL)
- Sivakumar, J., Muga, J., Spadavecchia, F., White, D., & Can, B. (2021). A GRU-based Pipeline Approach for Word-Sentence Segmentation and Punctuation Restoration in English. In 2021 International Conference on Asian Language Processing (IALP) (pp. 268-273). Institute of Electrical and Electronics Engineers. (IEEE)
Curriculum Vitae
Find a full CV here.
Education
PhD Computer Science (Natural Language Processing)
Sep 21 - Sep 26
University of Sheffield, UK
MA Computational Linguistics - Distinction
Sep 20 - Sep 21
University of Wolverhampton, UK
PGCE Secondary Education (Mathematics)
Sep 17 - Sep 18
University of Cambridge, UK
Bachelors (MMath) Mathematics - First Class
Oct 12 - Jul 16
University of Warwick, UK
(Year abroad: Université Pierre et Marie Curie, France)
Research Activities
NLP for Endangered Language Revitalisation
Sep 21 - Sep 26
- Collect and digitise text data using OCR for an endangered afro-colombia language, Palenquero.
- Deploy low-resource language NLP research to develop pedagogical resources.
Speech Technology and NLP to improve Oral History Search Functionality
Nov 21 - Jun 22
- Project with oral history video archive to train ASR systems for transcription.
- Adapted NER systems to identify naval domain specific terms and improve transcription search.
- Pipeline ASR, diarisation and NER systems to provide annotated transcript used to give desired timestamps with videos.
Professional Experience
Applied Scientist (Amazon - Alexa International)
Sep 25 - Dec 25
Bellevue, Washington, USA
Trained reward models for RL using generated multilingual, multistyle cultural preference data. Conducted human preference annotation to highlight that human and foundational models preferences are uncorrelated, and depend on language and style.
Research Scientist (Huawei - Noah's Ark Lab)
Apr 25 - Sep 25
London, UK
Achieved first end-to-end autoformalisation and proof of 13 PutnamBench problems by developing decoupled conjecture-reasoning pipelines using few-shot prompting and parallel Lean4 Chain-of-Thought.
Applied Scientist (Amazon - Alexa International)
Jul 24 - Oct 24
Bellevue, Washington, USA
Optimised foundational models (Claude, Llama, Mistral) with AWS by engineering human-in-the-loop output relevancy benchmark creation process for any language. Collaborated with cross-functional teams to deploy production-ready material.
Consultant (University of Sheffield)
Jan 24 - Jun 26
Sheffield, South Yorkshire, UK
Architected and designed scalable AI solutions, including RAG for automated query response, Topic Modeling for complex document analysis, and speech-signal stress detection, while advising clients on cost-efficiency and technical stability
Teacher of Mathematics (Abbey College)
Sep 18 - Aug 21
Ramsey, Cambridgeshire, UK
Led Key Stage 5 curriculum development and university preparation, including entrance exam coaching, while mentoring trainee teachers and delivering departmental upskilling initiatives for staff.
Language Teacher (Universidad de Sucre)
Aug 17 - Jun 18
Sincelejo, Sucre, Colombia
Lectured French and English culture and language courses (A1 to C2), preparing students for official certifications and supervising student teachers on pedagogical action-research projects.
