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)

[CSS] The impact of DDoS and other security shocks on Bitcoin currency exchanges: Evidence from Mt. Gox

Amir Feder, Neil Gandal, JT Hamrick, Tyler Moore

Journal of Cybersecurity, 2018 [pdf]

[CSS] The rise and fall of cryptocurrencies

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

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

[CSS] An examination of the cryptocurrency pump-and-dump ecosystem

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

Information Processing & Management, 2019 [pdf]

[LM] Active deep learning to detect demographic traits in free-form clinical notes

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

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

[CSS, LM] Predicting In-game Actions from Interviews of NBA Players

Amir Feder*, Nadav Oved*, Roi Reichart

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

[LM, CI] Are VQA systems RAD? measuring robustness to augmented data with focused interventions

Daniel Rosenberg, Itai Gat, Amir Feder, Roi Reichart

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

[LM, CI] CausaLM: Causal model explanation through counterfactual language models

Amir Feder, Nadav Oved, Uri Shalit, Roi Reichart

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

[LM] Learning and evaluating a differentially private pre-trained language model

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]

[LM, CI] Model compression for domain adaptation through causal effect estimation

Guy Rotman*, Amir Feder*, Roi Reichart

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

[LM, CI] On Calibration and Out-of-domain Generalization

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

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

[LM] Structured Understanding of Assessment and Plans in Clinical Documentation

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]

[CSS, LM] Shared computational principles for language processing in humans and deep language models

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]

[LM, CI] DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation

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

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

[LM, CSS, CI] Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond

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

[LM] Useful Confidence Measures: Beyond the Max Score

Gal Yona, Amir Feder, Itay Laish

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

[LM] Section Classification in Clinical Notes with Multi-task Transformers

Fan Zhang, Itay Laish, Ayelet Benjamini, Amir Feder

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

[LM] Building a Clinically-Focused Problem List From Medical Notes

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]

[LM, CI] CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

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

[CSS, LM, CI] In the Eye of the Beholder: Robust Prediction with Causal User Modeling

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

Neural information processing systems (NeurIPS) 2022 [arxiv]

[LM, CI] An Invariant Learning Characterization of Controlled Text Generation

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]

[CSS, LM] Evaluating the Moral Beliefs Encoded in LLMs

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

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

[LM, CI] 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]

[LM] LLMs Accelerate Annotation for Medical Information Extraction

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

[LM, CI] Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals

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]

[CSS, LM] Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns

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]

[LM] Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?

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

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

[LM] Exploring the Learning Capabilities of Language Models using LEVERWORLDS
Eitan Wagner, Amir Feder, Omri Abend
Empirical Methods in Natural Language Processing (EMNLP) 2024

Under Review

[LM] CoverBench: A Challenging Benchmark for Complex Claim Verification

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

[arxiv]

[CSS, LM] Can LLMs Learn Macroeconomic Narratives from Social Media?

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:

Ph.D.
- Itamar Trainin (Hebrew U, co-advised by Roy Schwartz)
- Zach Bamberger (Technion, co-advised by Ofra Amir)
M.Sc.
- Yuval Shalev (Hebrew U, co-advised by Ariel Goldstein)

Teaching

Lecturer

Technion - Israel Institute of Technology
- [097215] Natural Language Processing (2021-2022)

Teaching Assistant
- Technion - Israel Institute of Technology
  - [236756] Foundations of Machine Learning (2020-2021)
- Tel Aviv University
  - Econometrics and Causal Analysis (2015-2016)
  - Monetary Economics (2015-2016)
  - The Macroeconomic Environment, Kellogg-Recanati International MBA (2015-2016)

Tutorials:

Tutorial on Causal Inference for NLP, EMNLP 2022

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

Workshops:

NLP for Science (NLP4S), EMNLP 2024

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

Spurious Correlations, Invariance and Stability (SCIS), ICML 2023

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

First Workshop on Causal Inference & NLP (CI+NLP), EMNLP 2021

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]