@inproceedings{zur2024updating,title={Updating CLIP to Prefer Descriptions Over Captions},author={Zur, Amir and Kreiss, Elisa and D'Oosterlinck, Karel and Potts, Christopher and Geiger, Atticus},editor={Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},month=nov,year={2024},address={Miami, Florida, USA},publisher={Association for Computational Linguistics},url={https://aclanthology.org/2024.emnlp-main.1125},pages={20178--20187},}
@article{geiger2024causalabstractiontheoreticalfoundation,title={Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability},author={Geiger, Atticus and Ibeling, Duligur and Zur, Amir and Chaudhary, Maheep and Chauhan, Sonakshi and Huang, Jing and Arora, Aryaman and Wu, Zhengxuan and Goodman, Noah and Potts, Christopher and Icard, Thomas},year={2024},eprint={2301.04709},archiveprefix={arXiv},primaryclass={cs.AI},url={https://arxiv.org/abs/2301.04709},}
@inproceedings{wu2023causal,title={Causal proxy models for concept-based model explanations},author={Wu, Zhengxuan and D’Oosterlinck, Karel and Geiger, Atticus and Zur, Amir and Potts, Christopher},booktitle={International conference on machine learning},pages={37313--37334},year={2023},organization={PMLR},}
@article{zur2023meta,title={Meta-Learning for Better Learning: Using Meta-Learning Methods to Automatically Label Exam Questions with Detailed Learning Objectives.},author={Zur, Amir and Applebaum, Isaac and Nardo, Jocelyn Elizabeth and DeWeese, Dory and Sundrani, Sameer and Salehi, Shima},journal={International Educational Data Mining Society},year={2023},publisher={ERIC},}
Causal Abstraction for Interpretable, Debiased, and Accessible Language Models
Amir Zur
Linguistics Honors Thesis, Stanford University, Nov 2023