Buchumschlag

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

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Dentella, Vittoria, Guenther, Fritz, Leivada, Evelina
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

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

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

Large Language Model probabilities cannot distinguish between possible and impossible language
von: Leivada, Evelina, et al.
Veröffentlicht: (2025)

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

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

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

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

Positional Cognitive Specialization: Where Do LLMs Learn To Comprehend and Speak Your Language?
von: Salim, Luis Frentzen, et al.
Veröffentlicht: (2026)

Why Larger Language Models Do In-context Learning Differently?
von: Shi, Zhenmei, et al.
Veröffentlicht: (2024)

An Assessment on Comprehending Mental Health through Large Language Models
von: Arcan, Mihael, et al.
Veröffentlicht: (2024)

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

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

Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models
von: Mekala, Dheeraj, et al.
Veröffentlicht: (2024)

Are Aligned Large Language Models Still Misaligned?
von: Naseem, Usman, et al.
Veröffentlicht: (2026)

Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning
von: Juneja, Gurusha, et al.
Veröffentlicht: (2023)

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

Seamless Deception: Larger Language Models Are Better Knowledge Concealers
von: Ashok, Dhananjay, et al.
Veröffentlicht: (2026)

Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models
von: Zhang, Zihong, et al.
Veröffentlicht: (2025)

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

Should We Still Pretrain Encoders with Masked Language Modeling?
von: Gisserot-Boukhlef, Hippolyte, et al.
Veröffentlicht: (2025)

Large Language Models Still Exhibit Bias in Long Text
von: Jeung, Wonje, et al.
Veröffentlicht: (2024)

Do Language Models Agree with Human Perceptions of Suspense in Stories?
von: Matlin, Glenn, et al.
Veröffentlicht: (2025)

Do Language Models Know When They're Hallucinating References?
von: Agrawal, Ayush, et al.
Veröffentlicht: (2023)

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

Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images
von: Mahanta, Cristina, et al.
Veröffentlicht: (2025)

Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models
von: Setty, Vinay
Veröffentlicht: (2024)

Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled
von: Lin, Yi-Chien, et al.
Veröffentlicht: (2025)

Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis
von: Diera, Andor, et al.
Veröffentlicht: (2026)

Too Big to Fail: Larger Language Models are Disproportionately Resilient to Induction of Dementia-Related Linguistic Anomalies
von: Li, Changye, et al.
Veröffentlicht: (2024)

Surprisal from Larger Transformer-based Language Models Predicts fMRI Data More Poorly
von: Lin, Yi-Chien, et al.
Veröffentlicht: (2025)

Large Language Models Perform on Par with Experts Identifying Mental Health Factors in Adolescent Online Forums
von: Lorge, Isabelle, et al.
Veröffentlicht: (2024)

RoParQ: Paraphrase-Aware Alignment of Large Language Models Towards Robustness to Paraphrased Questions
von: Choi, Minjoon
Veröffentlicht: (2025)

Do Large Language Models Judge Error Severity Like Humans?
von: Sun, Diege, et al.
Veröffentlicht: (2025)

Do Language Models Exhibit Human-like Structural Priming Effects?
von: Jumelet, Jaap, et al.
Veröffentlicht: (2024)

When Do Language Models Endorse Limitations on Human Rights Principles?
von: Samway, Keenan, et al.
Veröffentlicht: (2026)

Large Language Models Are Still Misled by Simple Bias Ensembles
von: Sun, Zhouhao, et al.
Veröffentlicht: (2025)

Humans vs Vision-Language Models: A Unified Measure of Narrative Coherence
von: Ilinykh, Nikolai, et al.
Veröffentlicht: (2026)

Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language
von: Ariai, Farid, et al.
Veröffentlicht: (2025)

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