| 2026 | EACL | Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions. | Pedro Henrique Luz de Araujo, Michael A. Hedderich, Ali Modarressi, Hinrich Schtze, Benjamin Roth |
| 2025 | ACL | Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence. | Mohsen Fayyaz, Ali Modarressi, Hinrich Schtze, Nanyun Peng |
| 2025 | ACL | Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models. | Ahmad Dawar Hakimi, Ali Modarressi, Philipp Wicke, Hinrich Schtze |
| 2025 | ACL | MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment. | Amir Hossein Kargaran, Ali Modarressi, Nafiseh Nikeghbal, Jana Diesner, Franois Yvon, Hinrich Schtze |
| 2025 | EMNLP | ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge. | Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma, Hinrich Schtze |
| 2025 | EMNLP | Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing. | Raoyuan Zhao, Abdullatif Kksal, Ali Modarressi, Michael A. Hedderich, Hinrich Schtze |
| 2025 | ICML | NoLiMa: Long-Context Evaluation Beyond Literal Matching. | Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Trung Bui, Ryan A. Rossi, Seunghyun Yoon, Hinrich Schtze |
| 2024 | EMNLP | Consistent Document-level Relation Extraction via Counterfactuals. | Ali Modarressi, Abdullatif Kksal, Hinrich Schtze |
| 2023 | ACL | DecompX: Explaining Transformers Decisions by Propagating Token Decomposition. | Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar |
| 2023 | EACL | Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities. | Ali Modarressi, Hossein Amirkhani, Mohammad Taher Pilehvar |
| 2022 | ACL | AdapLeR: Speeding up Inference by Adaptive Length Reduction. | Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar |
| 2022 | NAACL | GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers. | Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar |
| 2021 | EMNLP | Exploring the Role of BERT Token Representations to Explain Sentence Probing Results. | Hosein Mohebbi, Ali Modarressi, Mohammad Taher Pilehvar |