🧑‍🔬 Amir Feder

🏛️ Affiliations

🎓Columbia UniversityNew York · United States2021–2026 · 17 paperscurrent🏢GoogleMountain View · United States2020–2026 · 13 paperscurrent🏢GoogleHaifa · Israel2021–2026 · 6 paperscurrent🎓University of CambridgeCambridge · United Kingdom2026 · 2 paperscurrent🎓Hebrew University of JerusalemJerusalem · Israel2026 · 1 papercurrent🎓Technion – Israel Institute of TechnologyHaifa · Israel2018–2025 · 19 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions 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. Evaluating the Moral Beliefs Encoded in LLMs (2023 · 129 citations)
   The paper examines which moral preferences large language models reveal when treated as survey respondents. It also addresses two practical obstacles: models emit token strings rather than discrete choices, and their answers shift with prompt wording.
2. CausaLM: Causal Model Explanation Through Counterfactual Language Models (2021 · 107 citations)
   Explaining what drives a neural text classifier is hard. Standard attribution tools measure correlation, not causation, so they cannot separate the influence of two related high-level concepts, such as a politician's name and the adjectives around it. A proper causal estimate requires counterfactual texts, which…
3. Predicting In-Game Actions from Interviews of NBA Players (2020 · 24 citations)
   Sports analytics usually forecasts player behavior from historical statistics alone and ignores what athletes say off the court.
4. Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders (2026)
   Classic topic models such as LDA work on word counts, and most neural variants still present topics as ranked word lists.

All works

14 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Shared computational principles for language processing in humans and deep language models ↗Nature Neuroscience · no summary yetAriel Goldstein et al.2022 · 494 citations
2. Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond ↗arXiv:2109.00725 · no summary yetAmir Feder et al.2021 · 309 citations
3. Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations? ↗arXiv:2405.05904 · no summary yetZorik Gekhman et al.2024 · 171 citations
4. Evaluating the Moral Beliefs Encoded in LLMsConference on Neural Information Processing Systems (NeurIPS)Nino Scherrer, Claudia Shi, Amir Feder, et al.2023 · 129 citations
5. CausaLM: Causal Model Explanation Through Counterfactual Language ModelsComputational LinguisticsAmir Feder, Nadav Oved, Uri Shalit, et al.2021 · 107 citations
6. Thinking ahead: spontaneous prediction in context as a keystone of language in humans and machines ↗bioRxiv (Cold Spring Harbor Laboratory) · no summary yetAriel Goldstein et al.2020 · 56 citations
7. 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
8. Predicting In-Game Actions from Interviews of NBA PlayersComputational LinguisticsNadav Oved, Amir Feder, Roi Reichart2020 · 24 citations
9. Correspondence between the layered structure of deep language models and temporal structure of natural language processing in the human brain ↗bioRxiv (Cold Spring Harbor Laboratory) · no summary yetAriel Goldstein et al.2022 · 22 citations
10. Temporal structure of natural language processing in the human brain corresponds to layered hierarchy of large language models ↗Nature Communications · no summary yetAriel Goldstein et al.2025 · 17 citations
11. Data Augmentations for Improved (Large) Language Model Generalization ↗neural information processing systems · no summary yetAmir Feder et al.2023 · 8 citations
12. An Invariant Learning Characterization of Controlled Text Generation ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetCarolina Zheng et al.2023 · 7 citations
13. Model Directions, Not Words: Mechanistic Topic Models Using Sparse AutoencodersTransactions of the Association for Computational Linguistics (TACL)Carolina Zheng, Nicolas Beltran-Velez, Sweta Karlekar, et al.2026
14. Multi-environment Topic Models ↗arXiv (Cornell University) · no summary yetDominic Sobhani, Amir Feder, David M. Blei2024

🤝 Co-authors here

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

• Claudia Shi ×2
• David M. Blei ×2
• Nadav Oved ×2
• Roi Reichart ×2
• Nino Scherrer

Venues

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

• Computational Linguistics ×2: Computational Linguistics 2021, Computational Linguistics 2020
• bioRxiv (Cold Spring Harbor Laboratory) ×2
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2023
• Transactions of the Association for Computational Linguistics (TACL): Transactions of the Association for Computational Linguistics (TACL) 2026
• Nature Communications
• Nature Neuroscience
• Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 462 times (of the 149,439 papers whose bibliographies we read); 93 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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