Cover Image

Evolution and compression in LLMs: On the emergence of human-aligned categorization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Imel, Nathaniel, Zaslavsky, Noga
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

Agent-based imitation dynamics can yield efficiently compressed population-level vocabularies
by: Imel, Nathaniel, et al.
Published: (2026)

On convexity and efficiency in semantic systems
by: Imel, Nathaniel, et al.
Published: (2026)

Density, asymmetry and citation dynamics in scientific literature
by: Imel, Nathaniel, et al.
Published: (2025)

Semantic categories of artifacts and animals reflect efficient coding
by: Zaslavsky, Noga, et al.
Published: (2019)

How desirable is alignment between LLMs and linguistically diverse human users?
by: Knoeferle, Pia, et al.
Published: (2025)

Ranking LLMs by compression
by: Guo, Peijia, et al.
Published: (2024)

Annotation alignment: Comparing LLM and human annotations of conversational safety
by: Movva, Rajiv, et al.
Published: (2024)

Identifying and interpreting non-aligned human conceptual representations using language modeling
by: Bao, Wanqian, et al.
Published: (2024)

Strong and weak alignment of large language models with human values
by: Khamassi, Mehdi, et al.
Published: (2024)

Language models align with human judgments on key grammatical constructions
by: Hu, Jennifer, et al.
Published: (2024)

ZOQO: Zero-Order Quantized Optimization
by: Bar, Noga, et al.
Published: (2025)

Why are LLMs' abilities emergent?
by: Havlík, Vladimír
Published: (2025)

Grammar and Gameplay-aligned RL for Game Description Generation with LLMs
by: Tanaka, Tsunehiko, et al.
Published: (2025)

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
by: Wen, Zichen, et al.
Published: (2025)

Quantifying and extending the coverage of spatial categorization data sets
by: Li, Wanchun, et al.
Published: (2026)

Progressing beyond Art Masterpieces or Touristic Clichés: how to assess your LLMs for cultural alignment?
by: Branco, António, et al.
Published: (2026)

Few-shot Personalization of LLMs with Mis-aligned Responses
by: Kim, Jaehyung, et al.
Published: (2024)

What are human values, and how do we align AI to them?
by: Klingefjord, Oliver, et al.
Published: (2024)

Pragmatics beyond humans: meaning, communication, and LLMs
by: Gvoždiak, Vít
Published: (2025)

Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes
by: Cao, Jie, et al.
Published: (2019)

TouchAI: Exploring human-AI perceptual alignment in touch through language model representations
by: Zhong, Shu, et al.
Published: (2024)

Revealing emergent human-like conceptual representations from language prediction
by: Xu, Ningyu, et al.
Published: (2025)

Computational emotion analysis with multimodal LLMs: Current evidence on an emerging methodological opportunity
by: Licht, Hauke
Published: (2025)

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

Do LLMs produce texts with "human-like" lexical diversity?
by: Kendro, Kelly, et al.
Published: (2025)

Can LLMs capture stable human-generated sentence entropy measures?
by: Pivel-Villanueva, Estrella, et al.
Published: (2026)

Do LLMs write like humans? Variation in grammatical and rhetorical styles
by: Reinhart, Alex, et al.
Published: (2024)

Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation
by: Gkoumas, Dimitris, et al.
Published: (2024)

Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs
by: Pramanik, Vishal, et al.
Published: (2026)

Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment
by: Wu, Hanlin, et al.
Published: (2025)

Naturalistic measure of social norms alignment
by: Kostiuk, Yevhen, et al.
Published: (2026)

PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs
by: Cheng, Xilong, et al.
Published: (2025)

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
by: Zhang, Rui, et al.
Published: (2026)

A scale of conceptual orality and literacy: Automatic text categorization in the tradition of "Nähe und Distanz"
by: Emmrich, Volker
Published: (2025)

Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities
by: Kankowski, Florian, et al.
Published: (2025)

HumT DumT: Measuring and controlling human-like language in LLMs
by: Cheng, Myra, et al.
Published: (2025)

Clinical knowledge in LLMs does not translate to human interactions
by: Bean, Andrew M., et al.
Published: (2025)

Wikipedia in the Era of LLMs: Evolution and Risks
by: Huang, Siming, et al.
Published: (2025)

Can LLMs extract human-like fine-grained evidence for evidence-based fact-checking?
by: Jarolím, Antonín, et al.
Published: (2025)

Do LLMs exhibit human-like response biases? A case study in survey design
by: Tjuatja, Lindia, et al.
Published: (2023)