Copertina

Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Michaelov, James A., Levy, Roger P., Bergen, Benjamin K.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

N-gram-like Language Models Predict Reading Time Best
di: Michaelov, James A., et al.
Pubblicazione: (2026)

Emergent inabilities? Inverse scaling over the course of pretraining
di: Michaelov, James A., et al.
Pubblicazione: (2023)

Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics
di: Michaelov, James A., et al.
Pubblicazione: (2024)

On the Acquisition of Shared Grammatical Representations in Bilingual Language Models
di: Arnett, Catherine, et al.
Pubblicazione: (2025)

Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events
di: Michaelov, James A., et al.
Pubblicazione: (2025)

Disaggregation Reveals Hidden Training Dynamics: The Case of Agreement Attraction
di: Michaelov, James A., et al.
Pubblicazione: (2025)

How Open Must Language Models be to Enable Reliable Scientific Inference?
di: Michaelov, James A., et al.
Pubblicazione: (2026)

A Bit of a Problem: Measurement Disparities in Dataset Sizes Across Languages
di: Arnett, Catherine, et al.
Pubblicazione: (2024)

Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability
di: Chang, Tyler A., et al.
Pubblicazione: (2023)

Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models
di: Chang, Tyler A., et al.
Pubblicazione: (2025)

Do Large Language Models Exhibit Spontaneous Rational Deception?
di: Taylor, Samuel M., et al.
Pubblicazione: (2025)

Large Language Models Pass the Turing Test
di: Jones, Cameron R., et al.
Pubblicazione: (2025)

Goldfish: Monolingual Language Models for 350 Languages
di: Chang, Tyler A., et al.
Pubblicazione: (2024)

Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios
di: Du, Y., et al.
Pubblicazione: (2025)

LLM Circuit Analyses Are Consistent Across Training and Scale
di: Tigges, Curt, et al.
Pubblicazione: (2024)

Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models
di: Kryvosheieva, Daria, et al.
Pubblicazione: (2024)

Why do language models perform worse for morphologically complex languages?
di: Arnett, Catherine, et al.
Pubblicazione: (2024)

Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models
di: Jones, Cameron R., et al.
Pubblicazione: (2024)

Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs
di: Trott, Sean, et al.
Pubblicazione: (2026)

EVOKE: Emotion Vocabulary Of Korean and English
di: Jung, Yoonwon, et al.
Pubblicazione: (2026)

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior
di: Huang, Zeyi, et al.
Pubblicazione: (2026)

Does GPT-4 pass the Turing test?
di: Jones, Cameron R., et al.
Pubblicazione: (2023)

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
di: Khan, Mohammad Aflah, et al.
Pubblicazione: (2025)

Implicit Representations of Grammaticality in Language Models
di: Wang, Yingshan Susan, et al.
Pubblicazione: (2026)

Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
di: Nguyen, Thong, et al.
Pubblicazione: (2024)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures
di: Wang, Junxuan, et al.
Pubblicazione: (2024)

Post-Training Language Models for Crosslingual Consistency
di: Liu, Tianyu, et al.
Pubblicazione: (2026)

Explaining and Mitigating Crosslingual Tokenizer Inequities
di: Arnett, Catherine, et al.
Pubblicazione: (2025)

Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds
di: Jeong, Jihoon
Pubblicazione: (2026)

Architecture, Not Scale: Circuit Localization in Large Language Models
di: Venkatesh, Sohan
Pubblicazione: (2026)

Cross-Lingual Response Consistency in Large Language Models: An ILR-Informed Evaluation of Claude Across Six Languages
di: Baluta, Camelia
Pubblicazione: (2026)

The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage
di: Oh, Byung-Doh, et al.
Pubblicazione: (2025)

On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts
di: Qiu, Linlu, et al.
Pubblicazione: (2025)

Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data
di: Zhang, Jingyu, et al.
Pubblicazione: (2024)

Dissecting the Ullman Variations with a SCALPEL: Why do LLMs fail at Trivial Alterations to the False Belief Task?
di: Pi, Zhiqiang, et al.
Pubblicazione: (2024)

A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
di: Zhao, Raoyuan, et al.
Pubblicazione: (2025)

Leveraging Language Models for Emotion and Behavior Analysis in Education
di: Tanaka, Kaito, et al.
Pubblicazione: (2024)

Testing the Predictions of Surprisal Theory in 11 Languages
di: Wilcox, Ethan Gotlieb, et al.
Pubblicazione: (2023)

GPT-4 is judged more human than humans in displaced and inverted Turing tests
di: Rathi, Ishika, et al.
Pubblicazione: (2024)

Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties
di: Faisal, Fahim, et al.
Pubblicazione: (2024)