Imagen de Portada

Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Baroni, Marco, Cheng, Emily, de-Dios-Flores, Iria, Franzon, Francesca
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Principles of semantic and functional efficiency in grammatical patterning
por: Cheng, Emily, et al.
Publicado: (2024)

Evil twins are not that evil: Qualitative insights into machine-generated prompts
por: Rakotonirina, Nathanaël Carraz, et al.
Publicado: (2024)

The emergence of numerical representations in communicating artificial agents
por: Mihai, Daniela, et al.
Publicado: (2026)

Repetitions are not all alike: distinct mechanisms sustain repetition in language models
por: Mahaut, Matéo, et al.
Publicado: (2025)

The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models
por: Graichen, Nora, et al.
Publicado: (2026)

Referential communication in heterogeneous communities of pre-trained visual deep networks
por: Mahaut, Matéo, et al.
Publicado: (2023)

Tracing Computation Density in LLMs
por: Kervadec, Corentin, et al.
Publicado: (2026)

Stereotypical gender actions can be extracted from Web text
por: Herdağdelen, Amaç, et al.
Publicado: (2025)

A quantitative analysis of semantic information in deep representations of text and images
por: Acevedo, Santiago, et al.
Publicado: (2025)

Emergence of a High-Dimensional Abstraction Phase in Language Transformers
por: Cheng, Emily, et al.
Publicado: (2024)

Open Generative Large Language Models for Galician
por: Gamallo, Pablo, et al.
Publicado: (2024)

Exploring the encoding of linguistic representations in the Fully-Connected Layer of generative CNNs for Speech
por: Šegedin, Bruno Ferenc, et al.
Publicado: (2025)

Truth Knows No Language: Evaluating Truthfulness Beyond English
por: Figueras, Blanca Calvo, et al.
Publicado: (2025)

Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models
por: Macocco, Iuri, et al.
Publicado: (2025)

Enhancing Agricultural Machinery Management through Advanced LLM Integration
por: Johnson, Emily, et al.
Publicado: (2024)

Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM
por: Bianco, Francesca, et al.
Publicado: (2026)

MemoryPrompt: A Light Wrapper to Improve Context Tracking in Pre-trained Language Models
por: Rakotonirina, Nathanaël Carraz, et al.
Publicado: (2024)

Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs
por: Kervadec, Corentin, et al.
Publicado: (2026)

Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
por: Zhang, Chenchen
Publicado: (2026)

Identifying the sources of ideological bias in GPT models through linguistic variation in output
por: Walker, Christina, et al.
Publicado: (2024)

Transfer the linguistic representations from TTS to accent conversion with non-parallel data
por: Chen, Xi, et al.
Publicado: (2024)

Prediction hubs are context-informed frequent tokens in LLMs
por: Nielsen, Beatrix M. G., et al.
Publicado: (2025)

Modeling the human lexicon under temperature variations: linguistic factors, diversity and typicality in LLM word associations
por: Rodriguez, Maria Andueza, et al.
Publicado: (2026)

Is linguistically-motivated data augmentation worth it?
por: Groshan, Ray, et al.
Publicado: (2025)

Is it the end of (generative) linguistics as we know it?
por: Chesi, Cristiano
Publicado: (2024)

LengClaro2023: A Dataset of Administrative Texts in Spanish with Plain Language adaptations
por: Agüera-Marco, Belén, et al.
Publicado: (2025)

A Hard Nut to Crack: Idiom Detection with Conversational Large Language Models
por: Fornaciari, Francesca De Luca, et al.
Publicado: (2024)

Explainability of machine learning approaches in forensic linguistics: a case study in geolinguistic authorship profiling
por: Roemling, Dana, et al.
Publicado: (2024)

Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence
por: Bonnasse-Gahot, Laurent, et al.
Publicado: (2026)

Probing self-attention in self-supervised speech models for cross-linguistic differences
por: Gopinath, Sai, et al.
Publicado: (2024)

Quantifying the cross-linguistic effects of syncretism on agreement attraction
por: Turk, Utku, et al.
Publicado: (2026)

A conclusive remark on linguistic theorizing and language modeling
por: Chesi, Cristiano
Publicado: (2025)

Linguini: A benchmark for language-agnostic linguistic reasoning
por: Sánchez, Eduardo, et al.
Publicado: (2024)

Structural priming: An experimental paradigm for mapping linguistic representations
por: Zhenguang G. Cai, et al.
Publicado: (2024)

Large language models and linguistic intentionality
por: Grindrod, Jumbly
Publicado: (2024)

PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents
por: Wang, Minjia, et al.
Publicado: (2026)

TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation
por: Malettira, Prajna G., et al.
Publicado: (2026)

Universal computation is intrinsic to language model decoding
por: Lewandowski, Alex, et al.
Publicado: (2026)

Evaluating Polish linguistic and cultural competency in large language models
por: Dadas, Sławomir, et al.
Publicado: (2025)

Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLM agents
por: Swain, Sankalp Tattwadarshi, et al.
Publicado: (2025)