| Dynabench: Rethinking Benchmarking in NLP D Kiela, M Bartolo, Y Nie, D Kaushik, A Geiger, Z Wu, B Vidgen, G Prasad, ... NAACL 2021, 2021 | 442 | 2021 |
| MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions Z Zhong, Z Wu, CD Manning, C Potts, D Chen EMNLP 2023, 2023 | 151 | 2023 |
| Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis Z Wu, DC Ong AAAI 2021, 2020 | 96 | 2020 |
| Interpretability at scale: Identifying causal mechanisms in alpaca Z Wu, A Geiger, C Potts, ND Goodman NeurIPS 2023, 2023 | 92 | 2023 |
| DynaSent: A Dynamic Benchmark for Sentiment Analysis C Potts, Z Wu, A Geiger, D Kiela ACL 2021, 2020 | 86 | 2020 |
| Finding alignments between interpretable causal variables and distributed neural representations A Geiger, Z Wu, C Potts, T Icard, N Goodman CLeaR 2024, 2024 | 85 | 2024 |
| Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset D Ong, Z Wu, ZX Tan, M Reddan, I Kahhale, A Mattek, J Zaki IEEE Transactions on Affective Computing 2019, 2019 | 84 | 2019 |
| Inducing causal structure for interpretable neural networks A Geiger, Z Wu, H Lu, J Rozner, E Kreiss, T Icard, ND Goodman, C Potts ICML 2022, 2021 | 82 | 2021 |
| Rotating online behavior change interventions increases effectiveness but also increases attrition G Kovacs, Z Wu, MS Bernstein CSCW 2018, 2018 | 77 | 2018 |
| Mapping the increasing use of llms in scientific papers W Liang, Y Zhang, Z Wu, H Lepp, W Ji, X Zhao, H Cao, S Liu, S He, ... CoLM 2024, 2024 | 75 | 2024 |
| Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability A Geiger, D Ibeling, A Zur, M Chaudhary, S Chauhan, J Huang, A Arora, ... JMLR 2025, 2024 | 67* | 2024 |
| ReFT: Representation finetuning for language models Z Wu, A Arora, Z Wang, A Geiger, D Jurafsky, CD Manning, C Potts NeurIPS 2024 spotlight, 2024 | 63 | 2024 |
| CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior ED Abraham, K D'Oosterlinck, A Feder, YO Gat, A Geiger, C Potts, ... NeurIPS 2022, 2022 | 50 | 2022 |
| Rigorously Assessing Natural Language Explanations of Neurons J Huang, A Geiger, K D'Oosterlinck, Z Wu, C Potts EMNLP 2023 @BlackboxNLP, 2023 | 37 | 2023 |
| Causal Proxy Models for Concept-Based Model Explanations Z Wu, K D'Oosterlinck, A Geiger, A Zur, C Potts ICML 2023, 2022 | 37 | 2022 |
| Conservation of Procrastination: Do Productivity Interventions Save Time or Just Redistribute It? G Kovacs, DM Gregory, Z Ma, Z Wu, G Emami, J Ray, MS Bernstein CHI 2019, 2019 | 35 | 2019 |
| On explaining your explanations of bert: An empirical study with sequence classification Z Wu, DC Ong arXiv preprint arXiv:2101.00196, 2021 | 33 | 2021 |
| Zeroc: A neuro-symbolic model for zero-shot concept recognition and acquisition at inference time T Wu, M Tjandrasuwita, Z Wu, X Yang, K Liu, R Sosič, J Leskovec NeurIPS 2022, 2022 | 29 | 2022 |
| ReaSCAN: Compositional Reasoning in Language Grounding Z Wu, E Kreiss, D Ong, C Potts NeurIPS 2021, 2021 | 24 | 2021 |
| Structured Self-Attention Weights Encode Semantics in Sentiment Analysis Z Wu, TS Nguyen, DC Ong EMNLP 2020 @BlackboxNLP, 2020 | 24 | 2020 |
Christopher PottsProfessor of Linguistics and, by courtesy, of Computer ScienceVerified email at stanford.edu