| Semstamp: A semantic watermark with paraphrastic robustness for text generation AB Hou*, J Zhang*, T He*, Y Wang, YS Chuang, H Wang, L Shen, ... NAACL 2024, 2023 | 127 | 2023 |
| The language barrier: Dissecting safety challenges of llms in multilingual contexts L Shen, W Tan, S Chen, Y Chen, J Zhang, H Xu, B Zheng, P Koehn, ... Findings of ACL 2024, 2024 | 86 | 2024 |
| On the blind spots of model-based evaluation metrics for text generation T He*, J Zhang*, T Wang, S Kumar, K Cho, J Glass, Y Tsvetkov ACL 2023, 2022 | 54 | 2022 |
| k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text AB Hou, J Zhang, Y Wang, D Khashabi, T He Findings of ACL 2024, 2024 | 44 | 2024 |
| Self-[in] correct: Llms struggle with refining self-generated responses D Jiang, J Zhang, O Weller, N Weir, B Van Durme, D Khashabi AAAI 2025, 2024 | 39* | 2024 |
| On the zero-shot generalization of machine-generated text detectors X Pu, J Zhang, X Han, Y Tsvetkov, T He Findings of EMNLP 2023, 2023 | 30 | 2023 |
| Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements J Zhang, A Elgohary, A Magooda, D Khashabi, B Van Durme ICLR 2025, 2024 | 20 | 2024 |
| Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy AB Hou, H Du, Y Wang, J Zhang, Z Wang, PP Liang, D Khashabi, ... COLM 2025, 2025 | 17* | 2025 |
| Changes in tweet geolocation over time: A study with carmen 2.0 J Zhang, A DeLucia, M Dredze Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022 …, 2022 | 14 | 2022 |
| Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data J Zhang, M Marone, T Li, B Van Durme, D Khashabi NAACL 2025, 2024 | 13 | 2024 |
| Tur [k] ingBench: A Challenge Benchmark for Web Agents K Xu, Y Kordi, K Sanders, Y Wang, A Byerly, J Zhang, B Van Durme, ... NAACL 2025, 2024 | 13 | 2024 |
| Core: Robust factual precision with informative sub-claim identification Z Jiang, J Zhang, N Weir, S Ebner, M Wanner, K Sanders, D Khashabi, ... Findings of ACL 2025, 2024 | 12* | 2024 |
| Study of manifestation of civil unrest on Twitter A Chinta*, J Zhang*, A DeLucia, M Dredze, AL Buczak Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021 …, 2021 | 9 | 2021 |
| Rationalyst: Pre-training process-supervision for improving reasoning D Jiang, G Wang, Y Lu, A Wang, J Zhang, C Liu, B Van Durme, ... ACL 2025, 2024 | 6 | 2024 |
| Geo-seq2seq: Twitter user geolocation on noisy data through sequence to sequence learning J Zhang, A DeLucia, C Zhang, M Dredze Findings of the Association for Computational Linguistics: ACL 2023, 4778-4794, 2023 | 5 | 2023 |
| PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation J Zhang, J Glass, T He 🏆Best Paper Award, NeurIPS ENLSP Workshop 2022; StarSEM 2023, 2022 | 3 | 2022 |
| Certified Mitigation of Worst-Case LLM Copyright Infringement J Zhang, J Yu, M Marone, B Van Durme, D Khashabi EMNLP 2025, 2025 | 1 | 2025 |
| DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation W Tan, J Zhang, L Shen, D Khashabi, P Koehn NeurIPS 2024, 2024 | 1 | 2024 |
| Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models H Phan, X Yang, K Yao, J Zhang, S Bi, X Tang, M Khabsa, L Liu, D Lei arXiv preprint arXiv:2510.21978, 2025 | | 2025 |
| The Alignment Waltz: Jointly Training Agents to Collaborate for Safety J Zhang, H Wang, EM Smith, S Wang, A Sharaf, M Pasupuleti, ... arXiv preprint arXiv:2510.08240, 2025 | | 2025 |
Daniel KhashabiJohns Hopkins UniversityVerified email at jhu.edu
