🧑‍🔬 Zhengxuan Wu — all works

31 works · ← Zhengxuan Wu

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
26. Language Model Circuits Are Sparse in the Neuron Basis ↗arXiv (Cornell University) · no summary yetAryaman Arora et al.2026 · 4 citations
27. HyperSteer: Activation Steering at Scale with Hypernetworks ↗arXiv (Cornell University) · no summary yetSun, Jiuding et al.2025 · 4 citations
28. ADAG: Automatically Describing Attribution Graphs ↗arXiv (Cornell University) · no summary yetAryaman Arora et al.2026 · 1 citation
29. PreFT: Prefill-only finetuning for efficient inference ↗arXiv (Cornell University) · no summary yetAndrew Lanpouthakoun et al.2026
30. Generalization Dynamics of LM Pre-training ↗arXiv (Cornell University) · no summary yetJiaxin Wen et al.2026
31. Mechanistic interpretability and control for language models ↗Stanford Digital Repository · no summary yetZhengxuan Wu et al.2026

↑ back to top

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