"From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL." Sahar Admoni, Assaf Hallak, Yftah Ziser, Omer Ben-Porat, Ofra Amir. To appear in AAMAS 2026. "Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions." Guy Bar-Shalom, Fabrizio Frasca, Derek Lim, Yoav Gelberg, Yftah Ziser, Ran El-Yaniv, Gal Chechik, Haggai Maron. To appear in AAAI 2026. [Paper] "Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT." Guy Bar-Shalom, Fabrizio Frasca, Yaniv Galron, Yftah Ziser, Haggai Maron. NeurIPS 2025. [Paper] [Code] "Policy Optimized Text-to-Image Pipeline Design." Uri Gadot, Rinon Gal, Yftah Ziser, Gal Chechik, Shie Mannor. NeurIPS 2025. [Paper] "Iterative Multilingual Spectral Attribute Erasure." Shun Shao, Yftah Ziser, Zheng Zhao, Yifu QIU, Shay B Cohen, Anna Korhonen . EMNLP 2025. [Paper] [Code] "A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs." Shaona Ghosh, Amrita Bhattacharjee, Yftah Ziser, Christopher Parisien. EMNLP 2025. [Paper] "Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion." Anum Afzal, Florian Matthes, Gal Chechik and Yftah Ziser. Findings of ACL 2025. [Paper] [Code] "TSPRank: Bridging Pairwise and Listwise Methods with a Bilinear Travelling Salesman Model." Waylon Li, Yftah Ziser, Yifei Xie, Shay B Cohen, Tiejun Ma. KDD 2025, Research Track. [Paper] [Code] "Spectral Editing of Activations for Large Language Model Alignment." Yifu Qiu, Zheng Zhao, Yftah Ziser, Anna Korhonen, Edoardo Ponti and Shay Cohen. NeurIPS 2024. [Paper] [Code] "Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models." Zheng Zhao, Yftah Ziser and Shay Cohen. EMNLP 2024. [Paper] [Code] "Are Large Language Models Temporally Grounded?" Yifu Qiu, Zheng Zhao, Yftah Ziser, Anna Korhonen, Edoardo Ponti and Shay Cohen. NAACL 2024. [Paper] [Code] "Detecting and Mitigating Hallucinations in Multilingual Summarisation." Yifu Qiu, Yftah Ziser, Anna Korhonen, Edoardo Ponti and Shay Cohen. EMNLP 2023. [Paper] [Code] "A Joint Matrix Factorization Analysis of Multilingual Representations." Zheng Zhao, Yftah Ziser, Bonnie Webber and Shay Cohen. Findings of EMNLP 2023. [Paper] [Code] "Rant or Rave: Variation over Time in the Language of Online Reviews." Yftah Ziser, Bonnie Webber and Shay Cohen. LRE 2023. [Paper] [Code] "Erasure of Unaligned Attributes from Neural Representations." Shun Shao*, Yftah Ziser* and Shay Cohen. TACL 2023. [Paper] [Code] "BERT Is Not The Count: Learning to Match Mathematical Statements with Proofs." Waylon Li, Yftah Ziser, Maximin Coavoux and Shay Cohen. EACL 2023. [Paper] [Code] "Gold Doesn’t Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information." Shun Shao, Yftah Ziser and Shay Cohen. EACL 2023. [Paper] [Code] "Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents." Marcio Fonseca, Yftah Ziser and Shay Cohen. EMNLP 2022. [Paper] [Code] [Demo] "Understanding Domain Learning in Language Models Through Subpopulation Analysis." Zheng Zhao, Yftah Ziser and Shay Cohen. BlackboxNLP @ EMNLP 2022. [Paper] "Customized Pre-training for Domain Adaptation with Category Shift, with an Application to Aspect Extraction." Entony Lekhtman, Yftah Ziser and Roi Reichart. EMNLP 2021. [Paper] [Code] "WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation." Nachshon Cohen*, Oren Kalinsky*, Yftah Ziser* and Alessandro Moschitti. ACL 2021. [Paper] [Data] "Answering Product-Questions by Utilizing Questions from Other Contextually Similar Products." Ohad Rozen, David Carmel, Avihai Mejer, Vitali Mirkis, and Yftah Ziser. NAACL 2021. [Paper] [Data] "Humor Detection in Product Question Answering Systems." Yftah Ziser, Elad Kravi and David Carmel. SIGIR 2020. [Paper] [Data] "Task Refinement Learning for Improved Accuracy and Stability of Unsupervised Domain Adaptation." Yftah Ziser and Roi Reichart. ACL 2019. [Paper] [Code] "Deep Pivot-Based Modeling for Cross-language Cross-domain Transfer with Minimal Guidance." Yftah Ziser and Roi Reichart. EMNLP 2018. [Paper] "Pivot Based Language Modeling for Improved Neural Domain Adaptation." Yftah Ziser and Roi Reichart. NAACL 2018. [Paper] [Code] "Neural Structural Correspondence Learning for Domain Adaptation." Yftah Ziser and Roi Reichart. CoNLL 2017. [Paper] [Code]