Dan Friedman

32 papers A* 5Journal 20Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
SPLA: Block Sparse Plus Linear Attention for Long Context Modeling.
CoRR
Bailin Wang, Dan Friedman, Tao Lei, Chong Wang
2025 J jnl
Extracting Rule-based Descriptions of Attention Features in Transformers.
CoRR
Dan Friedman, Adithya Bhaskar, Alexander Wettig, Danqi Chen
2025 — conf
Representing Rule-based Chatbots with Transformers.
NAACL (Long Papers)
Dan Friedman, Abhishek Panigrahi, Danqi Chen
2024 J jnl
Continual Memorization of Factoids in Large Language Models.
CoRR
Howard Chen, Jiayi Geng, Adithya Bhaskar, Dan Friedman, Danqi Chen
2024 A* conf
Finding Transformer Circuits With Edge Pruning.
NeurIPS
Adithya Bhaskar, Alexander Wettig, Dan Friedman, Danqi Chen
2024 J jnl
Finding Transformer Circuits with Edge Pruning.
CoRR
Adithya Bhaskar, Alexander Wettig, Dan Friedman, Danqi Chen
2024 A* conf
Interpretability Illusions in the Generalization of Simplified Models.
ICML
Dan Friedman, Andrew Kyle Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
2024 J jnl
Representing Rule-based Chatbots with Transformers.
CoRR
Dan Friedman, Abhishek Panigrahi, Danqi Chen
2024 — conf
The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models.
ACL (1)
Adithya Bhaskar, Dan Friedman, Danqi Chen
2024 J jnl
The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models.
CoRR
Adithya Bhaskar, Dan Friedman, Danqi Chen
2024 J jnl
When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1.
CoRR
R. Thomas McCoy, Shunyu Yao, Dan Friedman, Mathew D. Hardy, Thomas L. Griffiths
2023 J jnl
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve.
CoRR
R. Thomas McCoy, Shunyu Yao, Dan Friedman, Matthew Hardy, Thomas L. Griffiths
2023 J jnl
Interpretability Illusions in the Generalization of Simplified Models.
CoRR
Dan Friedman, Andrew K. Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
2023 A* conf
Learning Transformer Programs.
NeurIPS
Dan Friedman, Alexander Wettig, Danqi Chen
2023 J jnl
Learning Transformer Programs.
CoRR
Dan Friedman, Alexander Wettig, Danqi Chen
2023 — conf
Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations.
ACL (1)
Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, He He
2023 J jnl
Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations.
CoRR
Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, He He
2023 J jnl
The Vendi Score: A Diversity Evaluation Metric for Machine Learning.
Trans. Mach. Learn. Res.
Dan Friedman, Adji Bousso Dieng
2022 A* conf
Finding Dataset Shortcuts with Grammar Induction.
EMNLP
Dan Friedman, Alexander Wettig, Danqi Chen
2022 J jnl
Finding Dataset Shortcuts with Grammar Induction.
CoRR
Dan Friedman, Alexander Wettig, Danqi Chen
2022 J jnl
The Vendi Score: A Diversity Evaluation Metric for Machine Learning.
CoRR
Dan Friedman, Adji Bousso Dieng
2021 — conf
Factual Probing Is [MASK]: Learning vs. Learning to Recall.
NAACL-HLT
Zexuan Zhong, Dan Friedman, Danqi Chen
2021 J jnl
Factual Probing Is [MASK]: Learning vs. Learning to Recall.
CoRR
Zexuan Zhong, Dan Friedman, Danqi Chen
2021 — conf
Single-dataset Experts for Multi-dataset Question Answering.
EMNLP (1)
Dan Friedman, Ben Dodge, Danqi Chen
2021 J jnl
Single-dataset Experts for Multi-dataset Question Answering.
CoRR
Dan Friedman, Ben Dodge, Danqi Chen
2019 A* conf
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks.
AAAI
Michihiro Yasunaga, Jungo Kasai, Rui Zhang, Alexander R. Fabbri, Irene Li, Dan Friedman, Dragomir R. Radev
2019 J jnl
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks.
CoRR
Michihiro Yasunaga, Jungo Kasai, Rui Zhang, Alexander R. Fabbri, Irene Li, Dan Friedman, Dragomir R. Radev
2019 — conf
Syntax-aware Neural Semantic Role Labeling with Supertags.
NAACL-HLT (1)
Jungo Kasai, Dan Friedman, Robert Frank, Dragomir R. Radev, Owen Rambow
2019 J jnl
Syntax-aware Neural Semantic Role Labeling with Supertags.
CoRR
Jungo Kasai, Dan Friedman, Robert Frank, Dragomir R. Radev, Owen Rambow
2017 J jnl
Deep density networks and uncertainty in recommender systems.
CoRR
Yoel Zeldes, Stavros Theodorakis, Efrat Solodnik, Aviv Rotman, Gil Chamiel, Dan Friedman
2017 — conf
Linguistically Rich Vector Representations of Supertags for TAG Parsing.
TAG
Dan Friedman, Jungo Kasai, R. Thomas McCoy, Robert Frank, Forrest Davis, Owen Rambow
1990 J jnl
Congestion control in BBN packet-switched networks.
Comput. Commun. Rev.
J. Robinson, Dan Friedman, Martha Steenstrup