Published in Findings of EMNLP 2025, 2025
Recommended citation: Roi Cohen, Russa Biswas, Gerard de Melo. "InFact: Informativeness Alignment for Improved LLM Factuality." Findings of EMNLP 2025.
Download Paper
Published in NeurIPS 2024, 2024
Recommended citation: Roi Cohen, Konstantin Dobler, Eden Biran, Gerard de Melo. "I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token." NeurIPS 2024.
Download Paper
Published in TACL 2024, 2024
Recommended citation: Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, Mor Geva. "Evaluating the Ripple Effects of Knowledge Editing in Language Models." TACL 2024.
Download Paper
Published in EMNLP 2023, 2023
Recommended citation: Roi Cohen, May Hamri, Mor Geva, Amir Globerson. "LM vs LM: Detecting Factual Errors via Cross-Examination." EMNLP 2023.
Download Paper
Published in Findings of EACL 2023, 2023
Recommended citation: Roi Cohen, Mor Geva, Jonathan Berant, Amir Globerson. "Crawling the Internal Knowledge-Base of Language Models." Findings of EACL 2023.
Download Paper
Published in Under review, NeurIPS 2026, 2026
Recommended citation: Roi Cohen, Yvan Carre, Nick Lechtenborger, Hendrik Droste, Lucas Kerschke, Russa Biswas, Gerard de Melo, Jan Buys. "Knowledgeless Language Models: Decoupling Linguistic Competence and Factual Knowledge." Under review, NeurIPS 2026.
Published in Under review, COLM 2026, 2026
Recommended citation: Roi Cohen, Omri Fahn, Gerard de Melo. "Uncertainty Beyond Geometry: Kernel-Based Functional Routing in LLMs." Under review, COLM 2026.
Published in Under review, ICML 2026, 2026
Recommended citation: Ben Shapira, Roi Cohen, Shang-Tse Chen, Mahmood Sharif. "StyleAT: Defending Face Recognition Against Semantic Attacks." Under review, ICML 2026.
Download Paper
Published in Under review, ICLR 2026, 2026
Recommended citation: Roi Cohen, Omri Fahn, Gerard de Melo. "Unifying Latent Uncertainty Signals in Large Language Models for Improved Factual Precision." Under review, ICLR 2026.
Download Paper
Published in ICML 2026 Workshop, 2026
Recommended citation: Roi Cohen et al. "Metacognition and the Source of Competence in Large Language Models." ICML 2026 Workshop. Extended version in preparation.