Image de couverture de livre

An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yoshida, Ryo, Isono, Shinnosuke, Someya, Taiga, Oseki, Yohei, Kuribayashi, Tatsuki
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision
par: Yoshida, Ryo, et autres
Publié: (2024)

If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?
par: Yoshida, Ryo, et autres
Publié: (2025)

Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models
par: Someya, Taiga, et autres
Publié: (2025)

Language Acquisition Device in Large Language Models
par: Mita, Masato, et autres
Publié: (2026)

Emergent Word Order Universals from Cognitively-Motivated Language Models
par: Kuribayashi, Tatsuki, et autres
Publié: (2024)

Psychometric Predictive Power of Large Language Models
par: Kuribayashi, Tatsuki, et autres
Publié: (2023)

Can Language Models Learn Typologically Implausible Languages?
par: Xu, Tianyang, et autres
Publié: (2025)

Dual Alignment Between Language Model Layers and Human Sentence Processing
par: Kuribayashi, Tatsuki, et autres
Publié: (2026)

Composition, Attention, or Both?
par: Yoshida, Ryo, et autres
Publié: (2022)

Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
par: Yoshida, Ryo, et autres
Publié: (2021)

Large Language Models Are Human-Like Internally
par: Kuribayashi, Tatsuki, et autres
Publié: (2025)

Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition
par: Mita, Masato, et autres
Publié: (2025)

Syntactic Learnability of Echo State Neural Language Models at Scale
par: Ueda, Ryo, et autres
Publié: (2025)

Can Input Attributions Explain Inductive Reasoning in In-Context Learning?
par: Ye, Mengyu, et autres
Publié: (2024)

Does Vision Accelerate Hierarchical Generalization in Neural Language Learners?
par: Kuribayashi, Tatsuki, et autres
Publié: (2023)

Rethinking the Relationship between the Power Law and Hierarchical Structures
par: Nakaishi, Kai, et autres
Publié: (2025)

On Representational Dissociation of Language and Arithmetic in Large Language Models
par: Kisako, Riku, et autres
Publié: (2025)

Syntactically-guided Information Maintenance in Sentence Comprehension
par: Isono, Shinnosuke, et autres
Publié: (2026)

What Kind of Language is Easy to Language-Model Under Curriculum Learning?
par: El-Naggar, Nadine, et autres
Publié: (2026)

BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency
par: Haga, Akari, et autres
Publié: (2024)

Can Language Models Induce Grammatical Knowledge from Indirect Evidence?
par: Oba, Miyu, et autres
Publié: (2024)

Information Locality as an Inductive Bias for Neural Language Models
par: Someya, Taiga, et autres
Publié: (2025)

Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages
par: El-Naggar, Nadine, et autres
Publié: (2025)

Information-Theoretic Storage Cost in Sentence Comprehension
par: Kajikawa, Kohei, et autres
Publié: (2026)

Is Structure Dependence Shaped for Efficient Communication?: A Case Study on Coordination
par: Kajikawa, Kohei, et autres
Publié: (2024)

Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
par: Kobayashi, Goro, et autres
Publié: (2023)

First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning
par: Aoki, Yoichi, et autres
Publié: (2024)

Exclusive Unlearning
par: Sasaki, Mutsumi, et autres
Publié: (2026)

To Drop or Not to Drop? Predicting Argument Ellipsis Judgments: A Case Study in Japanese
par: Ishizuki, Yukiko, et autres
Publié: (2024)

Clozing the Gap: Exploring Why Language Model Surprisal Outperforms Cloze Surprisal
par: Nair, Sathvik, et autres
Publié: (2026)

Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality
par: Harada, Yuto, et autres
Publié: (2025)

Revisiting Real-Time Digging-In Effects: No Evidence from NP/Z Garden-Paths
par: Maina-Kilaas, Amani, et autres
Publié: (2026)

Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
par: Gao, Rena, et autres
Publié: (2025)

Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention
par: Li, Andrew, et autres
Publié: (2024)

Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times
par: Oh, Byung-Doh, et autres
Publié: (2024)

The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage
par: Oh, Byung-Doh, et autres
Publié: (2025)

Towards Harnessing Large Language Models for Comprehension of Conversational Grounding
par: Jokinen, Kristiina, et autres
Publié: (2024)

The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
par: Momen, Omar, et autres
Publié: (2026)

ERAS: Evaluating the Robustness of Chinese NLP Models to Morphological Garden Path Errors
par: Li, Qinchan, et autres
Publié: (2024)

Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models
par: Kando, Shunsuke, et autres
Publié: (2025)