From the 1 of 6 linked papers with an AI index.
6 papers
We Hebben Een Serieus Translatie: Modeling Intercomprehension as Probabilistic Inference
Thomas Hikaru Clark, Edward Gibson, Roger Levy
The paper proposes a Bayesian noisy‑channel model that uses a monolingual language model and a noise component to infer word mappings between related languages, explaining how spea…
Readers make targeted regressions to plausible errors in reanalysis of "noisy-channel garden-path" sentences
Thomas Hikaru Clark, Roger Levy, Edward Gibson
A key question in psycholinguistics is how inferences about the meaning of linguistic input unfold incrementally a comprehender's mind. In this work, we study reading dynamics for…
Greedy or not, here I come: Language production under vocabulary constraints in humans and resource-rational models
Thomas Hikaru Clark, Sihan Chen, Laura Nicolae
Communicating using only a limited vocabulary is a common but challenging cognitive phenomenon, requiring an ideal communicator to plan carefully to optimize for intelligibility wh…
To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times
Thomas Hikaru Clark, Carlos Arriaga, Javier Conde +2
Large Language Models (LLMs) have recently been shown to produce estimates of psycholinguistic norms, such as valence, arousal, or concreteness, for words and multiword expressions…
Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings
Javier Conde, MarÃa Grandury, Tairan Fu +7
Word-level psycholinguistic norms lend empirical support to theories of language processing. However, obtaining such human-based measures is not always feasible or straightforward.…
Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models
Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin +17
The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- espec…