Kyle Mahowald

30 papers · 2020–2026 · 7 conferences · across top CS/AI conferences

Achievements

🗺️ Taxonomy Completionist (46) 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (5) 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (6) 🏆 Keyword Champion (2) 🧬 Topic Evolution 📈 Trend Setter ⚡ Prolific Year (5) 💎 Century Club (29) 🔥 Unstoppable (6) ❓ The Questioner (8) 🗃️ Keyword Collector (122)

Conferences

EMNLP (14) ACL (6) NAACL (4) EACL (3) CONLL (1) ICLR (1) NIPS (1)

Top co-authors

Junyi Jessy Li (5) Christopher Potts (4) Venkata S Govindarajan (4) Richard Futrell (4) Tiago Pimentel (3) Juan Diego Rodriguez (3) Isabel Papadimitriou (3) Kanishka Misra (3) Kaj Bostrom (2) Ryan Cotterell (2)

Research topics

Linguistics (2)

Keywords

language model (7) large language model (4) contextual embedding (3) lexical semantics (2) text generation (2) zero-shot learning (2) subword tokenization (2) information theory (2) syntactic analysis (2) intergroup bia (2) grammatical construction (2) social media analysis (1) information bottleneck (1) kl divergence (1) in-context learning (1) natural language processing (1) representation learning (1) natural language inference (1) semantic analysis (1) video captioning (1)

Papers

From sunblock to softblock: Analyzing the correlates of neology in published writing and on social media EACL 2026

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning ICLR 2025

Constructions are Revealed in Word Distributions EMNLP 2025

Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs ACL 2025

Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025

Causal Interventions Reveal Shared Structure Across English Filler–Gap Constructions EMNLP 2025

Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently EMNLP 2024

Do *they* mean ‘us’? Interpreting Referring Expression variation under Intergroup Bias EMNLP 2024

Mission: Impossible Language Models ACL 2024

Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs EMNLP 2024

For Generated Text, Is NLI-Neutral Text the Best Text? EMNLP 2023

A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces ACL 2023

Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training ACL 2023

Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias ACL 2023

Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways CONLL 2023

A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction EACL 2023

Revisiting the Optimality of Word Lengths EMNLP 2023

Elaborative Simplification as Implicit Questions Under Discussion EMNLP 2023

Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways EMNLP 2023

Counterfactually Probing Language Identity in Multilingual Models EMNLP 2023

When classifying grammatical role, BERT doesn’t care about word order... except when it matters ACL 2022

What do tokens know about their characters and how do they know it? NAACL 2022

longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks. NAACL 2022

Investigating Information-Theoretic Properties of the Typology of Spatial Demonstratives NAACL 2022

Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality EMNLP 2022

How (Non-)Optimal is the Lexicon? NAACL 2021

A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space EMNLP 2021

Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT EACL 2021

Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP NIPS 2021

With Little Power Comes Great Responsibility EMNLP 2020