Cover Image

Large Language Model probabilities cannot distinguish between possible and impossible language

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Leivada, Evelina, Montero, Raquel, Morosi, Paolo, Moskvina, Natalia, Serrano, Tamara, Aguilar, Marcel, Guenther, Fritz
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Quantification and object perception in Multimodal Large Language Models and human linguistic cognition
by: Montero, Raquel, et al.
Published: (2025)

Multilingual Large Language Models do not comprehend all natural languages to equal degrees
by: Moskvina, Natalia, et al.
Published: (2026)

Community size rather than grammatical complexity better predicts Large Language Model accuracy in a novel Wug Test
by: Pantelidou, Nikoleta, et al.
Published: (2025)

Tracing the ongoing emergence of human-like reasoning in Large Language Models
by: Morosi, Paolo, et al.
Published: (2026)

Language in Vivo vs. in Silico: Size Matters but Larger Language Models Still Do Not Comprehend Language on a Par with Humans Due to Impenetrable Semantic Reference
by: Dentella, Vittoria, et al.
Published: (2024)

Testing AI on language comprehension tasks reveals insensitivity to underlying meaning
by: Dentella, Vittoria, et al.
Published: (2023)

A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds?
by: Leivada, Evelina, et al.
Published: (2023)

Language models as tools for investigating the distinction between possible and impossible natural languages
by: Kallini, Julie, et al.
Published: (2025)

Fundamental Principles of Linguistic Structure are Not Represented by o3
by: Murphy, Elliot, et al.
Published: (2025)

ChatGPT-generated texts show authorship traits that identify them as non-human
by: Dentella, Vittoria, et al.
Published: (2025)

Studies with impossible languages falsify LMs as models of human language
by: Bowers, Jeffrey S., et al.
Published: (2025)

SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models
by: Nalbandyan, Grigor, et al.
Published: (2025)

Kallini et al. (2024) do not compare impossible languages with constituency-based ones
by: Hunter, Tim
Published: (2024)

What does it mean to understand language?
by: Casto, Colton, et al.
Published: (2025)

Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
by: King, Jack, et al.
Published: (2026)

The 20 questions game to distinguish large language models
by: Richardeau, Gurvan, et al.
Published: (2024)

On the scaling relationship between cloze probabilities and language model next-token prediction
by: Jacobs, Cassandra L., et al.
Published: (2026)

Dissociating language and thought in large language models
by: Mahowald, Kyle, et al.
Published: (2023)

Different types of syntactic agreement recruit the same units within large language models
by: Kryvosheieva, Daria, et al.
Published: (2025)

Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling
by: Zhuang, Chengxu, et al.
Published: (2024)

(Im)possibility of Automated Hallucination Detection in Large Language Models
by: Karbasi, Amin, et al.
Published: (2025)

Adapting Biomedical Abstracts into Plain language using Large Language Models
by: Gangavarapu, Haritha, et al.
Published: (2025)

Analyzing Large language models chatbots: An experimental approach using a probability test
by: Peruchini, Melise, et al.
Published: (2024)

Large Language Models in Targeted Sentiment Analysis
by: Rusnachenko, Nicolay, et al.
Published: (2024)

Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events
by: Michaelov, James A., et al.
Published: (2025)

Modeling the language cortex with form-independent and enriched representations of sentence meaning reveals remarkable semantic abstractness
by: Saha, Shreya, et al.
Published: (2025)

Jumper and trousers (a high-poly 3D model)
by: Moskvina, Mariia
Published: (2025)

Skaitmeninis mokymas – Lietuva tarp kitų Europos Sąjungos šalių
by: Julija Moskvina
Published: (2021)

Logical forms complement probability in understanding language model (and human) performance
by: Wang, Yixuan, et al.
Published: (2025)

Retrieval meets Long Context Large Language Models
by: Xu, Peng, et al.
Published: (2023)

Why Do Large Language Models (LLMs) Struggle to Count Letters?
by: Fu, Tairan, et al.
Published: (2024)

Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models
by: Kauf, Carina, et al.
Published: (2024)

Is There a Case for Conversation Optimized Tokenizers in Large Language Models?
by: Ferrando, Raquel, et al.
Published: (2025)

Language models align with brain regions that represent concepts across modalities
by: Ryskina, Maria, et al.
Published: (2025)

Consultation on Industrial Machine Faults with Large language Models
by: Boonmee, Apiradee, et al.
Published: (2024)

InstructionCP: A fast approach to transfer Large Language Models into target language
by: Chen, Kuang-Ming, et al.
Published: (2024)

Large language models have learned to use language
by: Lupyan, Gary
Published: (2025)

Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training
by: Pieler, Michael, et al.
Published: (2024)

Evalita-LLM: Benchmarking Large Language Models on Italian
by: Magnini, Bernardo, et al.
Published: (2025)

Large language models can consistently generate high-quality content for election disinformation operations
by: Williams, Angus R., et al.
Published: (2024)