Michael Hahn 0001
17 publications
6 venues
H Index 9
Affiliation
Saarland University, Department of Language Science and Technology, Saarbr cken, GermanyStanford University, Linguistics Department, CA, USA
University of Edinburgh, School of Informatics, UK
University of T bingen, Germany
Links
| Name | Venue | Year | citations |
|---|---|---|---|
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data.
|
EMNLP | 2025 | 4 |
| Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers.
|
ICML | 2025 | 23 |
| A Formal Framework for Understanding Length Generalization in Transformers.
|
ICLR | 2025 | 0 |
| Separations in the Representational Capabilities of Transformers and Recurrent Architectures.
|
NIPS/NeurIPS | 2024 | 26 |
| More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface.
|
ACL | 2024 | 1 |
| InversionView: A General-Purpose Method for Reading Information from Neural Activations.
|
NIPS/NeurIPS | 2024 | 9 |
| Why are Sensitive Functions Hard for Transformers?
|
ACL | 2024 | 54 |
| Information Locality in the Processing of Classifier-Noun Dependencies in Mandarin Chinese.
|
Cognitive Science | 2024 | 0 |
| The Expressive Capacity of State Space Models: A Formal Language Perspective.
|
NIPS/NeurIPS | 2024 | 32 |
| How Do Syntactic Statistics and Semantic Plausibility Modulate Local Coherence Effects.
|
Cognitive Science | 2023 | 1 |
| Explaining patterns of fusion in morphological paradigms using the memory-surprisal tradeoff.
|
Cognitive Science | 2022 | 4 |
| Modeling Fixation Behavior in Reading with Character-level Neural Attention.
|
Cognitive Science | 2022 | 1 |
| An Information-Theoretic Characterization of Morphological Fusion.
|
EMNLP | 2021 | 15 |
| RNNs can generate bounded hierarchical languages with optimal memory.
|
EMNLP | 2020 | 59 |
| Character-based Surprisal as a Model of Reading Difficulty in the Presence of Errors.
|
Cognitive Science | 2019 | 5 |
| An Information-Theoretic Explanation of Adjective Ordering Preferences.
|
Cognitive Science | 2018 | 45 |
| Modeling Human Reading with Neural Attention.
|
EMNLP | 2016 | 57 |