Imagen de Portada

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	van der Wal, Oskar, Lesci, Pietro, Muller-Eberstein, Max, Saphra, Naomi, Schoelkopf, Hailey, Zuidema, Willem, Biderman, Stella
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Suppressing Pink Elephants with Direct Principle Feedback
por: Castricato, Louis, et al.
Publicado: (2024)

Undesirable Biases in NLP: Addressing Challenges of Measurement
por: van der Wal, Oskar, et al.
Publicado: (2022)

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
por: Schaeffer, Rylan, et al.
Publicado: (2024)

Mechanistic?
por: Saphra, Naomi, et al.
Publicado: (2024)

SnakModel: Lessons Learned from Training an Open Danish Large Language Model
por: Zhang, Mike, et al.
Publicado: (2024)

Llemma: An Open Language Model For Mathematics
por: Azerbayev, Zhangir, et al.
Publicado: (2023)

When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training
por: Körner, Felicia, et al.
Publicado: (2026)

Hidden Breakthroughs in Language Model Training
por: Kangaslahti, Sara, et al.
Publicado: (2025)

DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers
por: Müller-Eberstein, Max, et al.
Publicado: (2025)

ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
por: Li, Victoria R., et al.
Publicado: (2024)

Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
por: Qin, Tian, et al.
Publicado: (2024)

Tending Towards Stability: Convergence Challenges in Small Language Models
por: Martinez, Richard Diehl, et al.
Publicado: (2024)

A Linguistically Motivated Analysis of Intonational Phrasing in Text-to-Speech Systems: Revealing Gaps in Syntactic Sensitivity
por: Pouw, Charlotte, et al.
Publicado: (2025)

Do Language Models Exhibit Human-like Structural Priming Effects?
por: Jumelet, Jaap, et al.
Publicado: (2024)

Propositional Logic for Probing Generalization in Neural Networks
por: Langedijk, Anna, et al.
Publicado: (2025)

Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0
por: Kloots, Marianne de Heer, et al.
Publicado: (2024)

Baryon correlations in Pythia
por: Lönnblad, Leif, et al.
Publicado: (2023)

Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns
por: Pauli, Amalie Brogaard, et al.
Publicado: (2026)

Hypernetworks for Personalizing ASR to Atypical Speech
por: Müller-Eberstein, Max, et al.
Publicado: (2024)

Can Humans Identify Domains?
por: Barrett, Maria, et al.
Publicado: (2024)

AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets
por: Lesci, Pietro, et al.
Publicado: (2024)

A Taxonomy of Transcendence
por: Abreu, Natalie, et al.
Publicado: (2025)

First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
por: Saphra, Naomi, et al.
Publicado: (2023)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
por: Sherborne, Tom, et al.
Publicado: (2023)

Fast Forwarding Low-Rank Training
por: Rahamim, Adir, et al.
Publicado: (2024)

Interpretability for Time Series Transformers using A Concept Bottleneck Framework
por: van Sprang, Angela, et al.
Publicado: (2024)

Latent State Models of Training Dynamics
por: Hu, Michael Y., et al.
Publicado: (2023)

Self-Directed Synthetic Dialogues and Revisions Technical Report
por: Lambert, Nathan, et al.
Publicado: (2024)

In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads
por: Pouw, Charlotte, et al.
Publicado: (2026)

Black Big Boxes: Tracing Adjective Order Preferences in Large Language Models
por: Jumelet, Jaap, et al.
Publicado: (2024)

Linguists should learn to love speech-based deep learning models
por: Kloots, Marianne de Heer, et al.
Publicado: (2025)

The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders
por: Sauter, Adrian, et al.
Publicado: (2025)

Bayesian Optimization of Pythia8 Tunes
por: Kadhim, Ali Al, et al.
Publicado: (2025)

El Inca y sus curacas: poliginia real y construcción del poder
por: Tom Zuidema
Publicado: (2008)

Na ante-sala da discriminação: o preço dos atributos de sexo ecor no Brasil (19891999)
por: Ciro Biderman
Publicado: (2004)

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

Grokking Group Multiplication with Cosets
por: Stander, Dashiell, et al.
Publicado: (2023)

The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity
por: Bradshaw, Louis, et al.
Publicado: (2025)

Temporary Use Restriction (Provisional) — IVO Framework
por: van der Wal, Ivo
Publicado: (2025)

A Featural Typology of Bantu Agreement
por: van der Wal, Jenneke
Publicado: (2022)