Michael Hahn

Orcid: 0000-0003-4828-4834

Affiliations:

Saarland University, Department of Language Science and Technology, Saarbrücken, Germany
Stanford University, Linguistics Department, CA, USA (former, PhD 2022)
University of Edinburgh, School of Informatics, UK (former)
University of Tübingen, Germany (former)

According to our database¹, Michael Hahn authored at least 53 papers between 2011 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning.

[BibT_eX]

[DOI]

CoRR, May, 2026

Barriers to Universal Reasoning With Transformers (And How to Overcome Them).

[BibT_eX]

[DOI]

CoRR, April, 2026

On the Ability of Transformers to Verify Plans.

[BibT_eX]

[DOI]

CoRR, March, 2026

Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors.

[BibT_eX]

[DOI]

Mark Rofin

Jalal Naghiyev

Michael Hahn

CoRR, March, 2026

Discovering Interpretable Algorithms by Decompiling Transformers to RASP.

[BibT_eX]

[DOI]

CoRR, February, 2026

Systematicity between Forms and Meanings across Languages Supports Efficient Communication.

[BibT_eX]

[DOI]

CoRR, January, 2026

Provably Learning Attention with Queries.

[BibT_eX]

[DOI]

CoRR, January, 2026

System-Mediated Attention Imbalances Make Vision-Language Models Say Yes.

[BibT_eX]

[DOI]

CoRR, January, 2026

When Does LoRA Reuse Work? Theoretical Limits and Mechanisms for Recycling LoRAs Without Data Access.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2026

Tug-of-war between idioms' figurative and literal interpretations in LLMs.

[BibT_eX]

[DOI]

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

2025

Softmax Transformers are Turing-Complete.

[BibT_eX]

[DOI]

CoRR, November, 2025

Benefits and Limitations of Communication in Multi-Agent Reasoning.

[BibT_eX]

[DOI]

CoRR, October, 2025

The Bayesian Origin of the Probability Weighting Function in Human Representation of Probabilities.

[BibT_eX]

[DOI]

CoRR, October, 2025

Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning.

[BibT_eX]

[DOI]

Xinting Huang

Michael Hahn

CoRR, August, 2025

Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness.

[BibT_eX]

[DOI]

CoRR, June, 2025

Tug-of-war between idiom's figurative and literal meanings in LLMs.

[BibT_eX]

[DOI]

CoRR, June, 2025

Born a Transformer - Always a Transformer?

[BibT_eX]

[DOI]

CoRR, May, 2025

Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B.

[BibT_eX]

[DOI]

CoRR, April, 2025

Emergent Stack Representations in Modeling Counter Languages Using Transformers.

[BibT_eX]

[DOI]

Utkarsh Tiwari

Aviral Gupta

Michael Hahn

CoRR, February, 2025

Born a Transformer - Always a Transformer? On the Effect of Pretraining on Architectural Abilities.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers.

[BibT_eX]

[DOI]

Alireza Amiri Bavandpour

Xinting Huang

Mark Rofin

Michael Hahn

Proceedings of the Forty-second International Conference on Machine Learning, 2025

A Formal Framework for Understanding Length Generalization in Transformers.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Language models can learn implicit multi-hop reasoning, but only if they have lots of training data.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Linguistic Structure from a Bottleneck on Sequential Information Processing.

[BibT_eX]

[DOI]

Richard Futrell

Michael Hahn

CoRR, 2024

The Expressive Capacity of State Space Models: A Formal Language Perspective.

[BibT_eX]

[DOI]

Yash Raj Sarrof

Yana Veitsman

Michael Hahn

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

InversionView: A General-Purpose Method for Reading Information from Neural Activations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Separations in the Representational Capabilities of Transformers and Recurrent Architectures.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Information Locality in the Processing of Classifier-Noun Dependencies in Mandarin Chinese.

[BibT_eX]

[DOI]

Hailin Hao

Yang Yang

Michael Hahn

Proceedings of the 46th Annual Meeting of the Cognitive Science Society, 2024

More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface.

[BibT_eX]

[DOI]

Siyu Tao

Lucia Donatelli

Michael Hahn

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Why are Sensitive Functions Hard for Transformers?

[BibT_eX]

[DOI]

Michael Hahn

Mark Rofin

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

A Cross-Linguistic Pressure for Uniform Information Density in Word Order.

[BibT_eX]

[DOI]

Trans. Assoc. Comput. Linguistics, 2023

A Theory of Emergent In-Context Learning as Implicit Structure Induction.

[BibT_eX]

[DOI]

Michael Hahn

Navin Goyal

CoRR, 2023

How Do Syntactic Statistics and Semantic Plausibility Modulate Local Coherence Effects.

[BibT_eX]

[DOI]

Hailin Hao

Michael Hahn

Elsi Kaiser

Proceedings of the 45th Annual Meeting of the Cognitive Science Society, 2023

2022

Crosslinguistic word order variation reflects evolutionary pressures of dependency and information locality.

[BibT_eX]

[DOI]

Michael Hahn

Yang Xu

CoRR, 2022

Modeling Fixation Behavior in Reading with Character-level Neural Attention.

[BibT_eX]

[DOI]

Songpeng Yan

Michael Hahn

Frank Keller

Proceedings of the 44th Annual Meeting of the Cognitive Science Society, 2022

Explaining patterns of fusion in morphological paradigms using the memory-surprisal tradeoff.

[BibT_eX]

[DOI]

Neil Rathi

Michael Hahn

Richard Futrell

Proceedings of the 44th Annual Meeting of the Cognitive Science Society, 2022

2021

Sensitivity as a Complexity Measure for Sequence Classification Tasks.

[BibT_eX]

[DOI]

Michael Hahn

Dan Jurafsky

Richard Futrell

Trans. Assoc. Comput. Linguistics, 2021

An Information-Theoretic Characterization of Morphological Fusion.

[BibT_eX]

[DOI]

Neil Rathi

Michael Hahn

Richard Futrell

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

2020

Theoretical Limitations of Self-Attention in Neural Sequence Models.

[BibT_eX]

[DOI]

Michael Hahn

Trans. Assoc. Comput. Linguistics, 2020

RNNs can generate bounded hierarchical languages with optimal memory.

[BibT_eX]

[DOI]

Christopher D. Manning

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020

2019

Tabula nearly rasa: Probing the linguistic knowledge of character-level neural language models trained on unsegmented text.

[BibT_eX]

[DOI]

Michael Hahn

Marco Baroni

Trans. Assoc. Comput. Linguistics, 2019

Estimating Predictive Rate-Distortion Curves via Neural Variational Inference.

[BibT_eX]

[DOI]

Michael Hahn

Richard Futrell

Entropy, 2019

Character-based Surprisal as a Model of Human Reading in the Presence of Errors.

[BibT_eX]

[DOI]

CoRR, 2019

Character-based Surprisal as a Model of Reading Difficulty in the Presence of Errors.

[BibT_eX]

[DOI]

Proceedings of the 41th Annual Meeting of the Cognitive Science Society, 2019

2018

Modeling Task Effects in Human Reading with Neural Attention.

[BibT_eX]

[DOI]

Michael Hahn

Frank Keller

CoRR, 2018

Wreath Products of Distributive Forest Algebras.

[BibT_eX]

[DOI]

Michael Hahn

Andreas Krebs

Howard Straubing

Proceedings of the 33rd Annual ACM/IEEE Symposium on Logic in Computer Science, 2018

An Information-Theoretic Explanation of Adjective Ordering Preferences.

[BibT_eX]

[DOI]

Proceedings of the 40th Annual Meeting of the Cognitive Science Society, 2018

2016

Modeling Human Reading with Neural Attention.

[BibT_eX]

[DOI]

Michael Hahn

Frank Keller

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016

2015

Henkin semantics for reasoning with natural language.

[BibT_eX]

[DOI]

Michael Hahn

Frank Richter

J. Lang. Model., 2015

Visibly Counter Languages and the Structure of NC<sup>1</sup>.

[BibT_eX]

[DOI]

Proceedings of the Mathematical Foundations of Computer Science 2015, 2015

2013

CoMeT: Integrating different levels of linguistic modeling for meaning assessment.

[BibT_eX]

[DOI]

Proceedings of the 7th International Workshop on Semantic Evaluation, 2013

2012

Evaluating the Meaning of Answers to Reading Comprehension Questions: A Semantics-Based Approach.

[BibT_eX]

[DOI]

Michael Hahn

Detmar Meurers

Proceedings of the Seventh Workshop on Building Educational Applications Using NLP, 2012

2011

On deriving semantic representations from dependencies: A Practical approach for evaluating meaning in learner corpora.

[BibT_eX]

[DOI]

Michael Hahn

Detmar Meurers

Proceedings of the Computational Dependency Theory [papers from the International Conference on Dependency Linguistics, 2011

Michael Hahn

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...