Dan Friedman

I am a machine learning researcher at Apple. I did my PhD in the Princeton Computer Science department, advised by Danqi Chen. Danqi Chen. For the summer and fall of 2023, I was a student researcher at Google Research, where I was advised by Asma Ghandeharioun and Andrew Lampinen. Before graduate school, I was a software engineer at Google and IBM, and before that I was an undergraduate at Yale where I worked with Bob Frank and Dragomir Radev, and received a BA in English.

My PhD research was partially supported by a Google PhD Fellowship and I was named a 2025 Siebel Scholar.

Email  /  Scholar  /  Twitter  /  Github

Publications and preprints

• Extracting Rule-based Descriptions of Attention Features in Transformers
  Dan Friedman, Adithya Bhaskar, Alexander Wettig, Danqi Chen
  preprint
  Paper | Code


• Representing Rule-based Chatbots with Transformers
  Dan Friedman, Abhishek Panigrahi, Danqi Chen
  NAACL 2025
  Paper | Code


• Finding Transformer Circuits with Edge Pruning
  Adithya Bhaskar, Alexander Wettig, Dan Friedman, Danqi Chen
  NeurIPS 2024 Spotlight
  Paper | Code


• Embers of autoregression show how large language models are shaped by the problem they are trained to solve
  R. Thomas McCoy, Shunyu Yao, Dan Friedman, Matthew Hardy, Thomas L. Griffiths
  PNAS 2024
  Paper | arXiv | Code


• The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
  Adithya Bhaskar, Dan Friedman, Danqi Chen
  ACL 2024
  Paper | Code


• Interpretability Illusions in the Generalization of Simplified Models
  Dan Friedman, Andrew Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
  ICML 2024
  Paper


• Learning Transformer Programs
  Dan Friedman, Alexander Wettig, Danqi Chen
  NeurIPS 2023 Oral
  Paper | Code | Talk | Interview on TWIML AI podcast


• Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations
  Chenglei Si*, Dan Friedman*, Nitish Joshi, Shi Feng, Danqi Chen, He He
  ACL 2023
  Paper | Code


• The Vendi Score: A Diversity Evaluation Metric for Machine Learning
  Dan Friedman, Adji Bousso Dieng
  Transactions of Machine Learning Research (TMLR) 2023
  Paper | Code


• Finding Dataset Shortcuts with Grammar Induction
  Dan Friedman, Alexander Wetting, Danqi Chen
  EMNLP 2022
  Paper | Code


• Single-dataset Experts for Multi-dataset Question Answering
  Dan Friedman, Ben Dodge, Danqi Chen
  EMNLP 2021
  Paper | Code


• Factual Probing is [MASK]: Learning vs. Learning to Recall
  Zexuan Zhong*, Dan Friedman*, Danqi Chen
  NAACL 2021
  Paper | Code


• Syntax-aware Neural Semantic Role Labeling with Supertags
  Jungo Kasai, Dan Friedman, Robert Frank, Dragomir Radev, Owen Rambow
  NAACL 2019
  Paper


• ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
  Michihiro Yasunaga, Jungo Kasai, Rui Zhang, Alexander R Fabbri, Irene Li, Dan Friedman, Dragomir R Radev
  AAAI 2019
  Paper | Project page


• Linguistically Rich Vector Representations of Supertags for TAG Parsing
  Dan Friedman^*, Jungo Kasai^*, R Thomas McCoy^*, Robert Frank, Forrest Davis, Owen Rambow
  Proceedings of the 13th International Workshop on Tree Adjoining Grammars and Related Formalisms 2017
  Paper