Amir Feder

I'm a postdoctoral fellow at Columbia University, working with David Blei. I'm currently also a visiting faculty researcher at Google. In 2025 I'll be joining the Hebrew University as an assistant professor of Computer Science.

I work on language models and causal inference, often for applications in computational social science. My research develops methods that integrate causality into language models, and facilitate scientific inquiry with text data. 


I received my PhD from the Technion, where I worked with Roi Reichart and Uri Shalit. Previously, I was an history, economics and statistics student at Tel Aviv University, the Hebrew University and Northwestern University. I was a co-organizer of the First workshop on NLP and Causal Inference (CI+NLP) at EMNLP 2021, and the tutorial on Causality for NLP at EMNLP 2022. 


email: amir.feder at columbia dot edu

[google scholar] [semantic scholar] [dblp] [github

Selected Publications

(*=equal contribution)


Evaluating the Moral Beliefs Encoded in LLMs

Nino Scherrer*, Claudia Shi*, Amir Feder, David Blei 

Neural information processing systems (NeurIPS) 2023 (Spotlight) [arxiv] [press]


Data Augmentations for Improved (Large) Language Model Generalization

Amir Feder*, Yoav Wald*, Claudia Shi, Suchi Saria, David Blei 

Neural information processing systems (NeurIPS) 2023 [arxiv] [pdf]


On Calibration and Out-of-domain Generalization

Yoav Wald*, Amir Feder*, Daniel Greenfeld, Uri Shalit

Neural information processing systems (NeurIPS) 2021  [arxiv] [pdf]


CausaLM: Causal model explanation through counterfactual language models

Amir Feder, Nadav Oved, Uri Shalit, Roi Reichart

Computational Linguistics (CL),  2021 [arxiv] [code] [data] [pdf]


Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond

Amir Feder*, Katherine A Keith*, Emaad Manzoor*, Reid Pryzant*, Dhanya Sridhar*, Zach Wood-Doughty*, Jacob Eisenstein*, Justin Grimmer*, Roi Reichart*, Margaret E Roberts*, Brandon M Stewart*, Victor Veitch*, Diyi Yang*

Transactions of the Association for Computational Linguistics (TACL), 2022 [arxiv] [reading list]


Tutorial on Causal Inference for NLP

Amir Feder*, Zhijing Jin*, Kun Zhang*

Empirical Methods in Natural Language Processing (EMNLP) 2022 [youtube] [slides (part 1), slides (part 2)]

Here's a Venn diagram describing my research (publication #s below):

All Publications 

(*=equal contribution, LM=Language Models, CI=Causal Inference, CSS= Computational Social Science)


Amir Feder, Neil Gandal, JT Hamrick, Tyler Moore 

Journal of Cybersecurity, 2018 [pdf]

Amir Feder, Neil Gandal, JT Hamrick, Tyler Moore, Marie Vasek  

Workshop on the Economics of Information Security (WEIS) 2018 [pdf]

JT Hamrick, Farhang Rouhi, Arghya Mukherjee, Amir Feder, Neil Gandal, Tyler Moore, Marie Vasek  

Information Processing & Management, 2019 [pdf]

Amir Feder, Danny Vainstein, Roni Rosenfeld, Tzvika Hartman, Avinatan Hassidim, Yossi Matias 

Journal of Biomedical Informatics (JBI), 2020 [data] [pdf]

Amir Feder*, Nadav Oved*, Roi Reichart 

Computational Linguistics (CL),  2020 [arxiv] [code] [pdf]

Daniel Rosenberg, Itai Gat, Amir Feder, Roi Reichart 

Association for Computational Linguistics (ACL) 2021  [arxiv] [code] [pdf]

Amir Feder, Nadav Oved, Uri Shalit, Roi Reichart 

Computational Linguistics (CL),  2021 [arxiv] [code] [data] [pdf]

Shlomo Hoory, Amir Feder, Avichai Tendler, Sofia Erell, Alon Peled-Cohen, Itay Laish, Hootan Nakhost, Uri Stemmer, Ayelet Benjamini, Avinatan Hassidim, Yossi Matias 

Findings of the Association for Computational Linguistics: EMNLP 2021 [pdf]

Guy Rotman*, Amir Feder*, Roi Reichart 

Transactions of the Association for Computational Linguistics (TACL), 2021 [arxiv] [code] [pdf]

Yoav Wald*, Amir Feder*, Daniel Greenfeld, Uri Shalit 

Neural information processing systems (NeurIPS) 2021 [arxiv] [pdf]

Doron Stupp, Ronnie Barequet, I-Ching Lee, Eyal Oren, Amir Feder, Ayelet Benjamini, Avinatan Hassidim, Yossi Matias, Eran Ofek, Alvin Rajkomar 

Machine Learning for Healthcare (ML4H) 2022 [arxiv]

Ariel Goldstein, Zaid Zada*, Eliav Buchnik*, Mariano Schain*, Amy Price*, Bobbi Aubrey*, Samuel A Nastase*, Amir Feder*, Dotan Emanuel*, Alon Cohen*, Aren Jansen, Harshvardhan Gazula, Gina Choe, Aditi Rao, Catherine Kim, Colton Casto, Lora Fanda, Werner Doyle, Daniel Friedman, Patricia Dugan, Lucia Melloni, Roi Reichart, Sasha Devore, Adeen Flinker, Liat Hasenfratz, Omer Levy, Avinatan Hassidim, Michael Brenner, Yossi Matias, Kenneth A Norman, Orrin Devinsky, Uri Hasson  

Nature Neuroscience 2022 [arxiv] [pdf]

Nitay Calderon, Eyal Ben-David, Amir Feder, Roi Reichart 

Association for Computational Linguistics (ACL) 2022 [arxiv] [code] [pdf]

Amir Feder*, Katherine A Keith*, Emaad Manzoor*, Reid Pryzant*, Dhanya Sridhar*, Zach Wood-Doughty*, Jacob Eisenstein*, Justin Grimmer*, Roi Reichart*, Margaret E Roberts*, Brandon M Stewart*, Victor Veitch*, Diyi Yang* 

Transactions of the Association for Computational Linguistics (TACL), 2022 [arxiv] [reading list

Gal Yona, Amir Feder, Itay Laish 

NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications [arxiv]

Fan Zhang, Itay Laish, Ayelet Benjamini, Amir Feder 

Proceedings of the 13th International Conference on Health Text Mining and Information Analysis (LOUHI), 2022 [pdf]

Amir Feder, Itay Laish, Shashank Agarwal, Uri Lerner, Aviel Atias, Cathy Cheung, Peter Clardy, Alon Peled-Cohen, Rachana Fellinger, Hengrui Liu, Lan Huong Nguyen, Birju Patel, Natan Potikha, Amir Taubenfeld, Liwen Xu, Seung Doo Yang, Ayelet Benjamini, Avinatan Hassidim 

Proceedings of the 13th International Conference on Health Text Mining and Information Analysis (LOUHI), 2022 [pdf]

Eldar David Abraham*, Karel D'Oosterlinck*, Amir Feder*, Yair Ori Gat*, Atticus Geiger*, Christopher Potts*, Roi Reichart*, Zhengxuan Wu* 

Neural information processing systems (NeurIPS) 2022 [arxiv] [data]v

Amir Feder, Guy Horowitz, Yoav Wald, Roi Reichart, and Nir Rosenfeld 

Neural information processing systems (NeurIPS) 2022 [arxiv

Claudia Shi*, Carolina Zheng*, Keyon Vafa, Amir Feder, David Blei 

Association for Computational Linguistics (ACL) 2023 [Spotlight at NeurIPS 2022 Workshop on Robustness in Sequence Modeling]

Nino Scherrer*, Claudia Shi*, Amir Feder, David Blei 

 Neural information processing systems (NeurIPS) 2023 (Spotlight) [arxiv] [press]

Amir Feder*, Yoav Wald*, Claudia Shi, Suchi Saria, David Blei  

Neural information processing systems (NeurIPS) 2023 [arxiv

Akshay Goel*, Almog Gueta*, Omry Gilon, Sofia Erell, Chang Liu, Lan Huong Nguyen, Xiaohong Hao, Bolous Jaber, Shashir Reddy, Jean Steiner, Itay Laish, Amir Feder 

Proceedings of the Machine Learning for Health Symposium (ML4H), 2023

Yair Gat*, Nitay Calderon*, Amir Feder, Alexander Chapanin, Amit Sharma, Roi Reichart  

Proceedings of the Twelfth International Conference on Learning Representations (ICLR), 2024 [arxiv] [pdf]

Ariel Goldstein, Avigail Dabush, Bobbi Aubrey, Mariano Schain, Samuel A. Nastase, Zaid Zada, Eric Ham, Zhuoqiao Hong, Amir Feder, Harshvardhan Gazula, Eliav Buchnik, Werner Doyle, Sasha Devore, Patricia Dugan, Daniel Friedman, Michael Brenner, Avinatan Hassidim, Orrin Devinsky, Adeen Flinker, Uri Hasson 

Nature Communications, 2024 [arxiv] [pdf

Zorik Gekhman, Gal Yona, Roee Aharoni, Matan Eyal, Amir Feder, Roi Reichart, Jonathan Herzig 

Empirical Methods in Natural Language Processing (EMNLP) 2024 [arxiv]


Under Review

Alon Jacovi, Moran Ambar, Eyal Ben-David, Uri Shaham, Amir Feder, Mor Geva, Dror Marcus, Avi Caciularu

[arxiv]

Almog Gueta, Amir Feder, Zorik Gekhman, Ariel Goldstein, Roi Reichart 

[arxiv]


Preprints


Correspondence between the layered structure of deep language models and temporal structure of natural language processing in the human brain

Ariel Goldstein, Eric Ham, Samuel A Nastase, Zaid Zada, Avigail Dabush, Bobbi Bobbi Aubrey, Mariano Schain, Harshvardhan Gazula, Amir Feder, Werner Doyle, Sasha Devore, Patricia Dugan, Daniel Friedman, Michael Brenner, Avinatan Hassidim, Orrin Devinsky, Adeen Flinker, Omer Levy, Uri Hasson [arxiv]


Distributional reasoning in LLMs: Parallel reasoning processes in multi-hop reasoning

Yuval Shalev, Amir Feder, Ariel Goldstein [arxiv]


Explaining Classifiers with Causal Concept Effect (CaCE)

Yash Goyal, Amir Feder, Uri Shalit, Been Kim

2019 [arxiv]

Students:


Teaching

Tutorials:

With Kun Zhang, Zhijing Jin [youtube] [slides (part 1), slides (part 2)]


Workshops:

With Nitay Calderon, Alex Chapanin, Rotem Dror, Ariel Goldstein, Anna Korhonen, Shir Lissak, Yaakov Ophir, Roi Reichart, Ilanit Sobol, Refael Tikochinski, Mor Ventura

With Yoav Wald, Claudia Shi, Aahlad Puli, Limor Gultchin, Mark Goldstein, Maggie Makar, Victor Veitch, Uri Shalit [url]

With Katherine Keith, Emaad Manzoor, Reid Pryzant, Dhanya Sridhar, Zach Wood-Doughty,
Jacob Eisenstein, Justin Grimmer, Roi Reichart, Molly Roberts, Uri Shalit, Brandon Stewart, Victor Veitch, Diyi Yang [url]