Copertina

Where meaning lives: Layer-wise accessibility of psycholinguistic features in encoder and decoder language models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tikhomirova, Taisiia, Wulff, Dirk U.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Addressing Longstanding Challenges in Cognitive Science with Language Models
di: Wulff, Dirk U., et al.
Pubblicazione: (2025)

Scaling laws for language encoding models in fMRI
di: Antonello, Richard, et al.
Pubblicazione: (2023)

Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs
di: Watson, Julia, et al.
Pubblicazione: (2024)

Machine individuality: Separating genuine idiosyncrasy from response bias in large language models
di: Kriegmair, Valentin, et al.
Pubblicazione: (2026)

Probing the contents of semantic representations from text, behavior, and brain data using the psychNorms metabase
di: Hussain, Zak, et al.
Pubblicazione: (2024)

Augmenting emotion features in irony detection with Large language modeling
di: Lin, Yucheng, et al.
Pubblicazione: (2024)

Layer-wise Regularized Dropout for Neural Language Models
di: Ni, Shiwen, et al.
Pubblicazione: (2024)

Fresh in memory: Training-order recency is linearly encoded in language model activations
di: Krasheninnikov, Dmitrii, et al.
Pubblicazione: (2025)

Can large language models understand uncommon meanings of common words?
di: Wu, Jinyang, et al.
Pubblicazione: (2024)

Layer-wise Positional Bias in Short-Context Language Modeling
di: Rahimi, Maryam, et al.
Pubblicazione: (2026)

Unsupervised Layer-wise Score Aggregation for Textual OOD Detection
di: Darrin, Maxime, et al.
Pubblicazione: (2023)

Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models
di: Aman, Tabinda, et al.
Pubblicazione: (2025)

Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning
di: Zimmerman, Julia Witte, et al.
Pubblicazione: (2024)

CONFLARE: CONFormal LArge language model REtrieval
di: Rouzrokh, Pouria, et al.
Pubblicazione: (2024)

Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction
di: Liu, Zhexiong, et al.
Pubblicazione: (2025)

Unsupervised decoding of encoded reasoning using language model interpretability
di: Fang, Ching, et al.
Pubblicazione: (2025)

Mechanistic Steering of LLMs Reveals Layer-wise Feature Vulnerabilities in Adversarial Settings
di: Das, Nilanjana, et al.
Pubblicazione: (2026)

Linguistic properties and model scale in brain encoding: from small to compressed language models
di: Oota, Subba Reddy, et al.
Pubblicazione: (2026)

Do language models capture implied discourse meanings? An investigation with exhaustivity implicatures of Korean morphology
di: Shin, Hagyeong, et al.
Pubblicazione: (2024)

AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing
di: Thillainathan, Sarubi, et al.
Pubblicazione: (2026)

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
di: Wu, Jialiang, et al.
Pubblicazione: (2025)

Continual Learning with Embedding Layer Surgery and Task-wise Beam Search using Whisper
di: Kwok, Chin Yuen, et al.
Pubblicazione: (2025)

Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding
di: Olak, Michal, et al.
Pubblicazione: (2026)

Post-training makes large language models less human-like
di: Binz, Marcel, et al.
Pubblicazione: (2026)

A cross-species neural foundation model for end-to-end speech decoding
di: Zhang, Yizi, et al.
Pubblicazione: (2025)

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

LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation
di: Hu, Haichuan, et al.
Pubblicazione: (2024)

The production of meaning in the processing of natural language
di: Agostino, Christopher J., et al.
Pubblicazione: (2026)

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

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
di: Kapadia, Shashank, et al.
Pubblicazione: (2026)

A decoder-only foundation model for time-series forecasting
di: Das, Abhimanyu, et al.
Pubblicazione: (2023)

Semantic uncertainty in advanced decoding methods for LLM generation
di: Foodeei, Darius, et al.
Pubblicazione: (2025)

Fluent dreaming for language models
di: Thompson, T. Ben, et al.
Pubblicazione: (2024)

Algorithmic progress in language models
di: Ho, Anson, et al.
Pubblicazione: (2024)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
di: Wen, Zhuofan, et al.
Pubblicazione: (2026)

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
di: Qin, Jiayu, et al.
Pubblicazione: (2025)

TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling
di: Nargund, Nisharg, et al.
Pubblicazione: (2026)

On the attribution of confidence to large language models
di: Keeling, Geoff, et al.
Pubblicazione: (2024)

Large language models and linguistic intentionality
di: Grindrod, Jumbly
Pubblicazione: (2024)

Daily and Weekly Periodicity in Large Language Model Performance and Its Implications for Research
di: Tschisgale, Paul, et al.
Pubblicazione: (2026)