🧑‍🔬 Zhengxuan Wu

🏛️ Affiliations

🎓Stanford UniversityStanford · United States2018–2026 · 46 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Interpretability at Scale: Identifying Causal Mechanisms in Alpaca (2023 · 81 citations)
   Causal-abstraction methods test whether a neural network actually implements a human-readable algorithm, but until now they had only been applied to small, task-specific models.
2. Rigorously Assessing Natural Language Explanations of Neurons (2023 · 30 citations)
   Natural-language descriptions of what individual neurons in large language models encode are appealing, but it is unclear whether they faithfully reflect model behavior.

All works

31 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Dynabench: Rethinking Benchmarking in NLP ↗Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetDouwe Kiela et al.2021 · 482 citations
2. MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetZexuan Zhong et al.2023 · 199 citations
3. DynaSent: A Dynamic Benchmark for Sentiment Analysis ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetChristopher Potts et al.2021 · 103 citations
4. Mapping the Increasing Use of LLMs in Scientific Papers ↗arXiv:2404.01268 · no summary yetWeixin Liang et al.2024 · 89 citations
5. Quantifying large language model usage in scientific papers ↗Nature Human Behaviour · no summary yetWeixin Liang et al.2025 · 81 citations
6. Interpretability at Scale: Identifying Causal Mechanisms in AlpacaConference on Neural Information Processing Systems (NeurIPS)Zhengxuan Wu, Atticus Geiger, Thomas Icard, et al.2023 · 81 citations
7. Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations ↗arXiv:2303.02536 · no summary yetAtticus Geiger et al.2023 · 81 citations
8. ReFT: Representation Finetuning for Language Models ↗arXiv:2404.03592 · no summary yetZhengxuan Wu et al.2024 · 74 citations
9. Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability ↗arXiv:2301.04709 · no summary yetAtticus Geiger et al.2023 · 65 citations
10. AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders ↗arXiv:2501.17148 · no summary yetZhengxuan Wu et al.2025 · 59 citations
11. Inducing Causal Structure for Interpretable Neural Networks ↗arXiv (Cornell University) · no summary yetAtticus Geiger et al.2021 · 53 citations
12. RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations ↗Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetJing Huang et al.2024 · 35 citations
13. Rigorously Assessing Natural Language Explanations of NeuronsBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLPJing Huang, Atticus Geiger, Karel D'Oosterlinck, et al.2023 · 30 citations
14. CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior ↗arXiv (Cornell University) · no summary yetEldar David Abraham et al.2022 · 29 citations
15. Causal Proxy Models for Concept-Based Model Explanations ↗arXiv (Cornell University) · no summary yetZhengxuan Wu et al.2022 · 27 citations
16. pyvene: A Library for Understanding and Improving PyTorch Models via Interventions ↗arXiv (Cornell University) · no summary yetZhengxuan Wu et al.2024 · 26 citations
17. Causal Distillation for Language Models ↗Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetZhengxuan Wu et al.2022 · 25 citations
18. Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training ↗Findings of the Association for Computational Linguistics: ACL 2023 · no summary yetJing Huang et al.2023 · 21 citations
19. ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation ↗Transactions of the Association for Computational Linguistics · no summary yetZhengxuan Wu, Christopher D. Manning, Christopher Potts2023 · 19 citations
20. ReaSCAN: Compositional Reasoning in Language Grounding ↗arXiv (Cornell University) · no summary yetZhengxuan Wu et al.2021 · 19 citations
21. ZeroC: A Neuro-Symbolic Model for Zero-Shot Concept Recognition and Acquisition at Inference Time ↗neural information processing systems · no summary yetTailin Wu et al.2022 · 11 citations
22. Improved Representation Steering for Language Models ↗neural information processing systems · no summary yetZhengxuan Wu et al.2025 · 9 citations
23. Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models ↗Proceedings of the 7th Workshop on Representation Learning for NLP · no summary yetZhengxuan Wu, Nelson F. Liu, Christopher Potts2022 · 8 citations
24. \textttpyvene: A Library for Understanding and Improving PyTorch Models via Interventions ↗Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations) · no summary yetZhengxuan Wu et al.2024 · 7 citations
25. A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments ↗arXiv (Cornell University) · no summary yetZhengxuan Wu et al.2024 · 5 citations

See all 31 works by Zhengxuan Wu →

🤝 Co-authors here

5 co-authors with a page, the most papers together first.

• Atticus Geiger ×2
• Christopher E. Potts ×2
• Jing Huang
• Karel D'Oosterlinck
• Noah D. Goodman

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ×3
• neural information processing systems ×2
• BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP: BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2023
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2023
• Findings of the Association for Computational Linguistics: ACL 2023
• Nature Human Behaviour
• Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
• Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
• Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
• Proceedings of the 7th Workshop on Representation Learning for NLP
• Stanford Digital Repository
• Transactions of the Association for Computational Linguistics

🔗 Cited by

Papers of our library cite their works 1,098 times (of the 149,439 papers whose bibliographies we read); 143 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhengxuan-wu/