Michael Hahn

65 papers A* 8B 6Journal 41Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
Discovering Interpretable Algorithms by Decompiling Transformers to RASP.
CoRR
Xinting Huang, Aleksandra Bakalova, Satwik Bhattamishra, William Merrill, Michael Hahn
2026 J jnl
On the Ability of Transformers to Verify Plans.
CoRR
Yash Raj Sarrof, Yupei Du, Katharina Stein, Alexander Koller, Sylvie Thiébaux, Michael Hahn
2026 J jnl
Provably Learning Attention with Queries.
CoRR
Satwik Bhattamishra, Kulin Shah, Michael Hahn, Varun Kanade
2026 J jnl
System-Mediated Attention Imbalances Make Vision-Language Models Say Yes.
CoRR
Tsan Tsai Chan, Varsha Suresh, Anisha Saha, Michael Hahn, Vera Demberg
2026 J jnl
Systematicity between Forms and Meanings across Languages Supports Efficient Communication.
CoRR
Doreen Osmelak, Yang Xu, Michael Hahn, Kate McCurdy
2026 — conf
Tug-of-war between idioms' figurative and literal interpretations in LLMs.
EACL (Volume 1: Long Papers)
Soyoung Oh, Xinting Huang, Mathis Pink, Michael Hahn, Vera Demberg
2026 J jnl
Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors.
CoRR
Mark Rofin, Jalal Naghiyev, Michael Hahn
2026 J jnl
When Does LoRA Reuse Work? Theoretical Limits and Mechanisms for Recycling LoRAs Without Data Access.
Trans. Mach. Learn. Res.
Mei-Yen Chen, Thi Thu Uyen Hoang, Michael Hahn, M. Saquib Sarfraz
2025 A* conf
A Formal Framework for Understanding Length Generalization in Transformers.
ICLR
Xinting Huang, Andy Yang, Satwik Bhattamishra, Yash Raj Sarrof, Andreas Krebs, Hattie Zhou, Preetum Nakkiran, Michael Hahn
2025 J jnl
Benefits and Limitations of Communication in Multi-Agent Reasoning.
CoRR
Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi, Guillaume Rabusseau, Michael Hahn
2025 J jnl
Born a Transformer - Always a Transformer?
CoRR
Yana Veitsman, Mayank Jobanputra, Yash Raj Sarrof, Aleksandra Bakalova, Vera Demberg, Ellie Pavlick, Michael Hahn
2025 J jnl
Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B.
CoRR
Aleksandra Bakalova, Yana Veitsman, Xinting Huang, Michael Hahn
2025 J jnl
Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning.
CoRR
Xinting Huang, Michael Hahn
2025 J jnl
Emergent Stack Representations in Modeling Counter Languages Using Transformers.
CoRR
Utkarsh Tiwari, Aviral Gupta, Michael Hahn
2025 A* conf
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data.
EMNLP
Yuekun Yao, Yupei Du, Dawei Zhu, Michael Hahn, Alexander Koller
2025 J jnl
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data.
CoRR
Yuekun Yao, Yupei Du, Dawei Zhu, Michael Hahn, Alexander Koller
2025 A* conf
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers.
ICML
Alireza Amiri Bavandpour, Xinting Huang, Mark Rofin, Michael Hahn
2025 J jnl
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers.
CoRR
Alireza Amiri Bavandpour, Xinting Huang, Mark Rofin, Michael Hahn
2025 J jnl
Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness.
CoRR
Mei-Yen Chen, Thi Thu Uyen Hoang, Michael Hahn, M. Saquib Sarfraz
2025 J jnl
Softmax Transformers are Turing-Complete.
CoRR
Hongjian Jiang, Michael Hahn, Georg Zetzsche, Anthony Widjaja Lin
2025 J jnl
The Bayesian Origin of the Probability Weighting Function in Human Representation of Probabilities.
CoRR
Xin Tong, Thi Thu Uyen Hoang, Xue-Xin Wei, Michael Hahn
2025 J jnl
Tug-of-war between idiom's figurative and literal meanings in LLMs.
CoRR
Soyoung Oh, Xinting Huang, Mathis Pink, Michael Hahn, Vera Demberg
2024 J jnl
A Formal Framework for Understanding Length Generalization in Transformers.
CoRR
Xinting Huang, Andy Yang, Satwik Bhattamishra, Yash Raj Sarrof, Andreas Krebs, Hattie Zhou, Preetum Nakkiran, Michael Hahn
2024 B conf
Information Locality in the Processing of Classifier-Noun Dependencies in Mandarin Chinese.
CogSci
Hailin Hao, Yang Yang, Michael Hahn
2024 A* conf
InversionView: A General-Purpose Method for Reading Information from Neural Activations.
NeurIPS
Xinting Huang, Madhur Panwar, Navin Goyal, Michael Hahn
2024 J jnl
InversionView: A General-Purpose Method for Reading Information from Neural Activations.
CoRR
Xinting Huang, Madhur Panwar, Navin Goyal, Michael Hahn
2024 J jnl
Linguistic Structure from a Bottleneck on Sequential Information Processing.
CoRR
Richard Futrell, Michael Hahn
2024 — conf
More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface.
ACL (1)
Siyu Tao, Lucia Donatelli, Michael Hahn
2024 — ed.
Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, SIGTYPE 2024, St. Julian's, Malta, March 22, 2024.
SIGTYPE
Michael Hahn, Alexey Sorokin, Ritesh Kumar, Andreas Scherbakov, Yulia Otmakhova, Jinrui Yang, Oleg Serikov, Priya Rani, Edoardo M. Ponti, Saliha Muradoglu, Rena Gao, Ryan Cotterell, Ekaterina Vylomova
2024 A* conf
Separations in the Representational Capabilities of Transformers and Recurrent Architectures.
NeurIPS
Satwik Bhattamishra, Michael Hahn, Phil Blunsom, Varun Kanade
2024 J jnl
Separations in the Representational Capabilities of Transformers and Recurrent Architectures.
CoRR
Satwik Bhattamishra, Michael Hahn, Phil Blunsom, Varun Kanade
2024 A* conf
The Expressive Capacity of State Space Models: A Formal Language Perspective.
NeurIPS
Yash Raj Sarrof, Yana Veitsman, Michael Hahn
2024 J jnl
The Expressive Capacity of State Space Models: A Formal Language Perspective.
CoRR
Yash Raj Sarrof, Yana Veitsman, Michael Hahn
2024 — conf
Why are Sensitive Functions Hard for Transformers?
ACL (1)
Michael Hahn, Mark Rofin
2024 J jnl
Why are Sensitive Functions Hard for Transformers?
CoRR
Michael Hahn, Mark Rofin
2023 J jnl
A Cross-Linguistic Pressure for Uniform Information Density in Word Order.
CoRR
Thomas Hikaru Clark, Clara Meister, Tiago Pimentel, Michael Hahn, Ryan Cotterell, Richard Futrell, Roger Levy
2023 J jnl
A Cross-Linguistic Pressure for Uniform Information Density in Word Order.
Trans. Assoc. Comput. Linguistics
Thomas Hikaru Clark, Clara Meister, Tiago Pimentel, Michael Hahn, Ryan Cotterell, Richard Futrell, Roger Levy
2023 J jnl
A Theory of Emergent In-Context Learning as Implicit Structure Induction.
CoRR
Michael Hahn, Navin Goyal
2023 B conf
How Do Syntactic Statistics and Semantic Plausibility Modulate Local Coherence Effects.
CogSci
Hailin Hao, Michael Hahn, Elsi Kaiser
2022 J jnl
Crosslinguistic word order variation reflects evolutionary pressures of dependency and information locality.
CoRR
Michael Hahn, Yang Xu
2022 B conf
Explaining patterns of fusion in morphological paradigms using the memory-surprisal tradeoff.
CogSci
Neil Rathi, Michael Hahn, Richard Futrell
2022 B conf
Modeling Fixation Behavior in Reading with Character-level Neural Attention.
CogSci
Songpeng Yan, Michael Hahn, Frank Keller
2021 — conf
An Information-Theoretic Characterization of Morphological Fusion.
EMNLP (1)
Neil Rathi, Michael Hahn, Richard Futrell
2021 J jnl
Sensitivity as a Complexity Measure for Sequence Classification Tasks.
CoRR
Michael Hahn, Dan Jurafsky, Richard Futrell
2021 J jnl
Sensitivity as a Complexity Measure for Sequence Classification Tasks.
Trans. Assoc. Comput. Linguistics
Michael Hahn, Dan Jurafsky, Richard Futrell
2020 — conf
RNNs can generate bounded hierarchical languages with optimal memory.
EMNLP (1)
John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning
2020 J jnl
RNNs can generate bounded hierarchical languages with optimal memory.
CoRR
John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning
2020 J jnl
Theoretical Limitations of Self-Attention in Neural Sequence Models.
Trans. Assoc. Comput. Linguistics
Michael Hahn
2019 J jnl
Character-based Surprisal as a Model of Human Reading in the Presence of Errors.
CoRR
Michael Hahn, Frank Keller, Yonatan Bisk, Yonatan Belinkov
2019 B conf
Character-based Surprisal as a Model of Reading Difficulty in the Presence of Errors.
CogSci
Michael Hahn, Frank Keller, Yonatan Bisk, Yonatan Belinkov
2019 J jnl
Estimating Predictive Rate-Distortion Curves via Neural Variational Inference.
Entropy
Michael Hahn, Richard Futrell
2019 J jnl
Tabula nearly rasa: Probing the Linguistic Knowledge of Character-Level Neural Language Models Trained on Unsegmented Text.
CoRR
Michael Hahn, Marco Baroni
2019 J jnl
Tabula nearly rasa: Probing the linguistic knowledge of character-level neural language models trained on unsegmented text.
Trans. Assoc. Comput. Linguistics
Michael Hahn, Marco Baroni
2019 J jnl
Theoretical Limitations of Self-Attention in Neural Sequence Models.
CoRR
Michael Hahn
2019 J jnl
Wreath Products of Distributive Forest Algebras.
CoRR
Michael Hahn, Andreas Krebs, Howard Straubing
2018 B conf
An Information-Theoretic Explanation of Adjective Ordering Preferences.
CogSci
Michael Hahn, Judith Degen, Noah D. Goodman, Dan Jurafsky, Richard Futrell
2018 J jnl
Modeling Task Effects in Human Reading with Neural Attention.
CoRR
Michael Hahn, Frank Keller
2018 A* conf
Wreath Products of Distributive Forest Algebras.
LICS
Michael Hahn, Andreas Krebs, Howard Straubing
2016 A* conf
Modeling Human Reading with Neural Attention.
EMNLP
Michael Hahn, Frank Keller
2016 J jnl
Modeling Human Reading with Neural Attention.
CoRR
Michael Hahn, Frank Keller
2015 J jnl
Henkin semantics for reasoning with natural language.
J. Lang. Model.
Michael Hahn, Frank Richter
2015 — conf
Visibly Counter Languages and the Structure of NC
MFCS (2)
Michael Hahn, Andreas Krebs, Klaus-Jörn Lange, Michael Ludwig
2013 — conf
CoMeT: Integrating different levels of linguistic modeling for meaning assessment.
SemEval@NAACL-HLT
Niels Ott, Ramon Ziai, Michael Hahn, Detmar Meurers
2012 — conf
Evaluating the Meaning of Answers to Reading Comprehension Questions: A Semantics-Based Approach.
BEA@NAACL-HLT
Michael Hahn, Detmar Meurers
2011 — conf
On deriving semantic representations from dependencies: A Practical approach for evaluating meaning in learner corpora.
DepLing
Michael Hahn, Detmar Meurers