Pelora - AI Research

ABOUT US

AI Research at the Frontier

Pelora is an AI research initiative founded by Ben Shapira and Roi Cohen. Our work spans LLM factuality, adversarial robustness, biomedical AI, and interpretability. With publications at top-tier venues and experience at top-tier industrial reserach labs, we combine deep theoretical foundations with real-world engineering to push the boundaries of AI.

0+ Publications

0 Top-Tier Venues

0 Research Labs

0+ Years Combined Experience

OUR WORK

Research Areas

LLM Factuality & Safety

Detecting and mitigating hallucinations in large language models. Our work on cross-examination, uncertainty modeling, and the [IDK] token has been published at EMNLP, NeurIPS, and TACL.

Adversarial Robustness & Vision

Defending machine learning models against semantic adversarial attacks. Our StyleAT framework protects face recognition systems from style-based perturbations while preserving model accuracy.

Biomedical & Multimodal AI

Building foundation models that bridge molecular, protein, and textual modalities. Our MAMMAL and BioVERSE architectures enable multi-modal reasoning for drug discovery and biomedical research.

Selected Publications

NeurIPS 2024 I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token Roi Cohen, Konstantin Dobler, Eden Biran, Gerard de Melo
TACL 2024 Evaluating the Ripple Effects of Knowledge Editing in Language Models Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, Mor Geva
EMNLP 2023 LM vs LM: Detecting Factual Errors via Cross-Examination Roi Cohen, May Hamri, Mor Geva, Amir Globerson
Findings EMNLP 2025 InFact: Informativeness Alignment for Improved LLM Factuality Roi Cohen, Russa Biswas, Gerard de Melo
Under Review, ICML 2026 StyleAT: Defending Face Recognition Against Semantic Attacks Ben Shapira, Roi Cohen, Shang-Tse Chen, Mahmood Sharif
arXiv 2024 MAMMAL: Molecular Aligned Multi-Modal Architecture and Language Yoel Shoshan, Moshiko Raboh, Michal Ozery-Flato, Vadim Ratner, Alex Golts, Jeffrey K. Weber, Ella Barkan, Simona Rabinovici-Cohen, Sagi Polaczek, Ido Amos, Ben Shapira, Liam Hazan, Matan Ninio, Sivan Ravid, Michael M. Danziger, Yosi Shamay, Sharon Kurant, Joseph A. Morrone, Parthasarathy Suryanarayanan, Michal Rosen-Zvi, Efrat Hexter
arXiv 2025 BioVERSE: Representation Alignment of Biomedical Modalities to LLMs Ching-Huei Tsou, Michal Ozery-Flato, Ella Barkan, Diwakar Mahajan, Ben Shapira
Under Review, ICLR 2026 Knowledgeless Language Models: Decoupling Linguistic Competence and Factual Knowledge Roi Cohen, Yvan Carre, Nick Lechtenborger et al.

THE TEAM

Meet the Founders

Ben Shapira

Co-Founder · AI Researcher

M.Sc. in Computer Science from Tel Aviv University, specializing in adversarial robustness and computer vision. Currently a Research Scientist at IBM Research. Previously a Data Science and Software Engineer at AlgoSec, integrating NLP and LLM systems into production environments. Former intelligence analyst at IDF Unit 8200.

Roi Cohen

Co-Founder · AI Researcher

PhD candidate in Computer Science at HPI & TU Berlin, researching LLM factuality, interpretability, and safety. M.Sc. from Tel Aviv University under Prof. Amir Globerson and Prof. Mor Geva. Former Research Scientist at IBM Research and intern at Microsoft. Published at NeurIPS, EMNLP, TACL, and EACL. Official NeurIPS and ACL reviewer. Featured in The Wall Street Journal. Former researcher at IDF Unit 8200.

GET IN TOUCH

Interested in Our Research?

Whether you're exploring collaboration opportunities, interested in our publications, or want to discuss the future of trustworthy AI — we'd love to hear from you.

Get in Touch

Advancing AI ThroughRigorous Research