← Authors

Dieuwke Hupkes

39 papers · 2018–2025 · 10 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (58) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) 🌍 Conference Polyglot (10) πŸƒ Academic Marathon (7) 🀝 Dynamic Duo (14) πŸ”¬ Deep Specialist (11) 🧬 Topic Evolution πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (150) ⚑ Prolific Year (8) πŸ”₯ Unstoppable (8) πŸ’Ž Century Club (39) ❓ The Questioner (3)

Conferences

EMNLP (13) ACL (10) CONLL (4) NAACL (3) EACL (2) IJCAI (2) IJCNLP (2) AACL (1) COLING (1) ICLR (1)

Top co-authors

Elia Bruni (14) Verna Dankers (8) Jaap Jumelet (7) Adina Williams (6) Lucas Weber (4) Willem Zuidema (3) Dennis Ulmer (2) Gautier Dagan (2) Kaiser Sun (2) Khuyagbaatar Batsuren (2)

Keywords

language model (11) neural network (7) recurrent neural network (6) attention mechanism (6) large language model (5) representation learning (4) compositional generalization (4) model evaluation (4) benchmark evaluation (3) language emergence (3) diagnostic classifier (3) sequence-to-sequence model (3) referential game (3) evaluation benchmark (2) model ranking (2) encoder-decoder architecture (2) shortcut learning (2) bias detection (2) instruction tuning (2) syntactic parsing (2)

Papers

Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models NAACL 2025
Compute Optimal Scaling of Skills: Knowledge vs Reasoning ACL 2025
Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges ACL 2025
Interpretability of Language Models via Task Spaces ACL 2024
Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning EMNLP 2023
Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication ICLR 2023
Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation EMNLP 2023
The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks EMNLP 2023
Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning CONLL 2023
The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks CONLL 2023
Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses EMNLP 2023
Text Characterization Toolkit (TCT) AACL 2022
The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study ACL 2022
Can Transformers Process Recursive Nested Constructions, Like Humans? COLING 2022
The Curious Case of Absolute Position Embeddings EMNLP 2022
Sparse Interventions in Language Models with Differentiable Masking EMNLP 2022
Text Characterization Toolkit (TCT) IJCNLP 2022
Co-evolution of language and agents in referential games EACL 2021
Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little EMNLP 2021
Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network EMNLP 2021
Attention vs non-attention for a Shapley-based explanation method NAACL 2021
Language Models Use Monotonicity to Assess NPI Licensing ACL 2021
Language Models Use Monotonicity to Assess NPI Licensing IJCNLP 2021
Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network CONLL 2021
Language Modelling as a Multi-Task Problem EACL 2021
Location Attention for Extrapolation to Longer Sequences ACL 2020
Compositionality Decomposed: How do Neural Networks Generalise? (Extended Abstract) IJCAI 2020
Internal and external pressures on language emergence: least effort, object constancy and frequency EMNLP 2020
The Grammar of Emergent Languages EMNLP 2020
On the Realization of Compositionality in Neural Networks ACL 2019
Transcoding Compositionally: Using Attention to Find More Generalizable Solutions ACL 2019
The emergence of number and syntax units in LSTM language models NAACL 2019
Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment CONLL 2019
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP ACL 2019
Assessing Incrementality in Sequence-to-Sequence Models ACL 2019
Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information EMNLP 2018
Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items EMNLP 2018
Visualisation and 'Diagnostic Classifiers' Reveal how Recurrent and Recursive Neural Networks Process Hierarchical Structure (Extended Abstract) IJCAI 2018
Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue EMNLP 2018