Nitisha Jain

About Me

I am a Postdoctoral Researcher at King’s College London working with Dr Albert Meroño Peñuela and Professor Elena Simperl in the Department of Informatics. With a PhD in Knowledge Graphs from the Hasso Plattner Institute, my research lies at the intersection of generative AI, neuro-symbolic reasoning, and AI safety.

At KCL, I lead work on multimodal representations grounded in structured knowledge within the EU Horizon MuseIT project - developing, fine-tuning and evaluating generative pipelines that span text, image, speech, 3D, and music modalities for cultural heritage applications.

I also actively contribute to the MLCommons Croissant project - co-chairing efforts on Responsible AI metadata and governance for trustworthy dataset documentation. My broader interests include evaluation and alignment of generative and agentic AI systems, interpretability, and building structured frameworks for transparent, human-centered AI.

Recent News

  • (Oct 2025) Delighted to share that our perspective paper Towards Deployment-Centric Multimodal AI Beyond Vision and Language has finally been published in Nature Machine Intelligence. This paper presents a roadmap for real-world multimodal AI across domains like healthcare, sustainability, and engineering - pleased to be part of this important collaboration led by the University of Sheffield and The Alan Turing Institute with collaborators from 22 institutions.
  • (Sept 2025) Attended the 4th Annual Symposium of the Turing Interest Group on Knowledge Graphs, featuring insightful talks on neuro-symbolic agents, multimodal knowledge graphs and the UK’s Grand Challenges in defence, sustainability and health.
  • (Aug 2025) Participated in the Neuro-Symbolic AI Summer School 2025 organized by Centaur AI, an intensive online program held on August 14–15 that brought together leading researchers to advance understanding of neuro-symbolic methods for reasoning, planning, and mathematical AI - gaining valuable insights into emerging approaches for hybrid intelligence (certificate).
  • (Jun 2025) Honoured to participate in the Responsible AI UK workshop on AI Regulation Assurance for Safety-Critical Systems - a prestigious forum uniting experts across disciplines to shape real-world applications of responsible and trustworthy AI. More details and my reflections in this LinkedIn post.
  • (May 2025) Our paper on An Annotation Protocol for Diachronic Evaluation of Semantic Drift in Disability Sources has been accepted at the Linguistic Annotation Workshop (LAW) 2025, which will be co-located with ACL 2025 in Vienna this year.
  • (Mar 2025) Our research manuscript proposing a neurosymbolic approach for generating interpretable embeddings has been accepted for publication in the Neurosymbolic AI Journal! (preprint here).
  • (Mar 2025) Thrilled to have attended AI UK 2025, the flagship annual event of the Alan Turing Institute, bringing together leading researchers, innovators, and policymakers shaping the future of AI in the UK - shared my highlights and reflections in this LinkedIn post.
  • (Feb 2025) Excited to attend the event AI Fringe 2025, organized alongside the AI Safety Summit in Paris, bringing together researchers, policymakers, and practitioners to explore the societal, ethical, and creative dimensions of AI.
  • (Dec 2024) Excited to share our paper on the Croissant metadata standard will be presented as a spotlight paper at NeurIPS 2024 (top ~3% of submissions).

Recent Publications

  • Liu, X., Zhang, J., Zhou, S. et al. : Towards deployment-centric multimodal AI beyond vision and language. Nature Machine Intelligence 2025. [Paper] [PDF]
  • Nitisha Jain, Antoine Domingues, Adwait Baokar, Albert Meroño Peñuela, Elena Simperl : Towards Interpretable Embeddings: Aligning Representations with Semantic Aspects. Neurosymbolic AI Journal 2025. [Paper]
  • Nitisha Jain, Chiara Di Bonaventura, Albert Meroño-Peñuela, Barbara McGillivray : An Annotation Protocol for Diachronic Evaluation of Semantic Drift in Disability Sources. Linguistic Annotation Workshop (LAW) 2025, Association for Computational Linguistics (ACL). [Paper]
  • Mubashara Akhtar, Omar Benjelloun, Costanza Conforti, Luca Foschini, Joan Giner-Miguelez, Pieter Gijsbers, Sujata Goswami, Nitisha Jain et al. : Croissant: A Metadata Format for ML-Ready Datasets. Neural Information Processing Systems (NeurIPS) 2024. [Paper] (Spotlight paper)
  • Elisavet Koutsiana, Ioannis Reklos, Kholoud Saad Alghamdi, Nitisha Jain, Albert Meroño-Peñuela, Elena Simperl : Talking Wikidata: Communication Patterns and Their Impact on Community Engagement in Collaborative Knowledge Graphs. Transactions on Graph Data & Knowledge, 2025. [Paper]
  • Elisavet Koutsiana, Tushita Yadav, Nitisha Jain, Albert Merono Penuela, Elena Simperl : Agreeing and disagreeing in collaborative knowledge graph construction: An analysis of Wikidata. Journal of Web Semantics, 2025. [Paper]
  • Nitisha Jain, Mubashara Akhtar, Joan Giner-Miguelez, Rajat Shinde, Omar Benjelloun, Elena Simperl et al. : A Standardized Machine-readable Dataset Documentation Format for Responsible AI. arXiv preprint 2024 arXiv:2407.16883
  • Mubashara Akhtar, Omar Benjelloun, Costanza Conforti, Pieter Gijsbers, Joan Giner-Miguelez, Nitisha Jain et al.: Croissant: A Metadata Format for ML-Ready Datasets. Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning (DEEM), 2024. [Paper]
  • Antoine Domingues, Nitisha Jain, Albert Meroño Peñuela, Elena Simperl: Bringing Back Semantics to Knowledge Graph Embeddings : An Interpretability Approach. Proceedings of the 18th International Conference on Neural-Symbolic Learning and Reasoning (NeSy), 2024. [Paper]
  • Jacopo de Berardinis, Valentina Anita Carriero, Nitisha Jain et al.: The Polifonia Ontology Network: Building a Semantic Backbone for Musical Heritage. Proceedings of the 22nd International Semantic Web Conference (ISWC), 2023. [Paper]
  • Bohui Zhang, Ioannis Reklos, Nitisha Jain, Albert Meroño Peñuela, Elena Simperl: Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata. Joint proceedings of the KBC-LM workshop and the LM-KBC challenge @ ISWC 2023. [Paper]

Miscellaneous

Service

  • PC member for the Semantics 2025 conference held in Vienna.

  • PC member for ANSyA 2025: 1st International Workshop on Advanced Neuro-Symbolic Applications, co-located with ECAI 2025 conference.

  • Organization of the Workshop on Generative Neuro-Symbolic AI (GeNeSy), co-located with ESWC 2024.

  • Sponsorship Chair of the ESWC 2024 conference along with Jan-Christoph Kalo.

  • Paper reviewing

    • 2025 : Semantic Web Journal, ISWC, Semantics, SemDH (ESWC)
    • 2024 : Semantics, AI4DH (ESWC)
    • 2023 : TKDD, Semantic Web Journal
    • 2022 : Semantic Web Journal, WebConference, ESWC, CIKM, LWDA,
    • Previously : EMNLP(2021) LWDA(2020), AAAI(2019).
  • PC member for AI4DH 2021 (held in conjunction with ICIAP 2021), SUKI 2022 (in conjunction with NAACL 2022).
  • Reviewed papers for Semantic Web Journal(2022), WebConference(2022), ESWC(2022), CIKM(2022), LWDA(2022), EMNLP(2021), LWDA(2020), AAAI(2019).
  • PC member for AI4DH 2021 (held in conjunction with ICIAP 2021), SUKI 2022 (in conjunction with NAACL 2022).

Teaching and Supervision

  • January 2025 - Teaching Assistant for Network Data Analysis (Masters lecture)
  • January 2025 - Teaching Assistant for Knowledge Engineering (Bachelors lecture)
  • January 2024 - Teaching Assistant for Network Data Analysis (Masters lecture)
  • Summer 2024 - Bringing Back Semantics to Knowledge Graph Embeddings : An Interpretability Approach (internship), Student : Antoine Domingues, MSc, ENSTA Paris
  • Summer 2023 - Evaluation of the understanding and knowledge of Large Language Models compared to Knowledge Graphs (internship), Albin Joyeux, MSc, ENSTA PAris
  • Summer 2023 - Collaborative Use Of Generative AI (internship), Student : Shantanu Suwarnkar