Copertina

Deconstructing sentence disambiguation by joint latent modeling of reading paradigms: LLM surprisal is not enough

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Paape, Dario, Linzen, Tal, Vasishth, Shravan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
di: Timkey, William, et al.
Pubblicazione: (2026)

Assessing effect sizes, variability, and power in the on-line study of language production
di: Audrey, Bürki, et al.
Pubblicazione: (2024)

What can LLMs tell us about the mechanisms behind polarity illusions in humans? Experiments across model scales and training steps
di: Paape, Dario
Pubblicazione: (2026)

Do Language Models' Words Refer?
di: Mandelkern, Matthew, et al.
Pubblicazione: (2023)

SPAWNing Structural Priming Predictions from a Cognitively Motivated Parser
di: Prasad, Grusha, et al.
Pubblicazione: (2024)

Manipulating language models' training data to study syntactic constraint learning: the case of English passivization
di: Leong, Cara Su-Yi, et al.
Pubblicazione: (2024)

Multilingual Prompting for Improving LLM Generation Diversity
di: Wang, Qihan, et al.
Pubblicazione: (2025)

Escaping the sentence-level paradigm in machine translation
di: Post, Matt, et al.
Pubblicazione: (2023)

Entailment Semantics Can Be Extracted from an Ideal Language Model
di: Merrill, William, et al.
Pubblicazione: (2022)

Evaluating In-Context Translation with Synchronous Context-Free Grammar Transduction
di: Petty, Jackson, et al.
Pubblicazione: (2026)

What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length
di: Tjuatja, Lindia, et al.
Pubblicazione: (2024)

In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax
di: Mueller, Aaron, et al.
Pubblicazione: (2023)

How Does Code Pretraining Affect Language Model Task Performance?
di: Petty, Jackson, et al.
Pubblicazione: (2024)

Attention-aware semantic relevance predicting Chinese sentence reading
di: Sun, Kun
Pubblicazione: (2024)

Large language models can disambiguate opioid slang on social media
di: Carpenter, Kristy A., et al.
Pubblicazione: (2026)

Power in Numbers: Robust reading comprehension by finetuning with four adversarial sentences per example
di: Marcus, Ariel
Pubblicazione: (2024)

Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment
di: Merrill, William, et al.
Pubblicazione: (2024)

Emergence of Linear Truth Encodings in Language Models
di: Ravfogel, Shauli, et al.
Pubblicazione: (2025)

Language Models Struggle to Use Representations Learned In-Context
di: Lepori, Michael A., et al.
Pubblicazione: (2026)

Rapid Word Learning Through Meta In-Context Learning
di: Wang, Wentao, et al.
Pubblicazione: (2025)

RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-Context
di: Petty, Jackson, et al.
Pubblicazione: (2025)

The Impact of Depth on Compositional Generalization in Transformer Language Models
di: Petty, Jackson, et al.
Pubblicazione: (2023)

Subword models struggle with word learning, but surprisal hides it
di: Bunzeck, Bastian, et al.
Pubblicazione: (2025)

Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?
di: Liu, Tong, et al.
Pubblicazione: (2023)

Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions
di: Ji, Yongyi, et al.
Pubblicazione: (2024)

Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time
di: Hu, Michael Y., et al.
Pubblicazione: (2026)

Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
di: Hu, Michael Y., et al.
Pubblicazione: (2025)

Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
di: Qiu, Linlu, et al.
Pubblicazione: (2025)

Variation of sentence length across time and genre
di: Rudnicka, Karolina
Pubblicazione: (2025)

POS-tagging to highlight the skeletal structure of sentences
di: Churakov, Grigorii
Pubblicazione: (2024)

Recovering document annotations for sentence-level bitext
di: Wicks, Rachel, et al.
Pubblicazione: (2024)

A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models
di: Eisape, Tiwalayo, et al.
Pubblicazione: (2023)

Thinking beyond the anthropomorphic paradigm benefits LLM research
di: Ibrahim, Lujain, et al.
Pubblicazione: (2025)

Generating bilingual example sentences with large language models as lexicography assistants
di: Merx, Raphael, et al.
Pubblicazione: (2024)

Are LLM-based methods good enough for detecting unfair terms of service?
di: Frasheri, Mirgita, et al.
Pubblicazione: (2024)

Decomposition of surprisal: Unified computational model of ERP components in language processing
di: Li, Jiaxuan, et al.
Pubblicazione: (2024)

Iti-Validator: A Guardrail Framework for Validating and Correcting LLM-Generated Itineraries
di: Gadbail, Shravan, et al.
Pubblicazione: (2025)

Early Transformers: A study on Efficient Training of Transformer Models through Early-Bird Lottery Tickets
di: Cheekati, Shravan
Pubblicazione: (2024)

Neural paraphrasing by automatically crawled and aligned sentence pairs
di: Globo, Achille, et al.
Pubblicazione: (2024)

Are most sentences unique? An empirical examination of Chomskyan claims
di: Ring, Hiram
Pubblicazione: (2025)