Image de couverture de livre

Extracting books from production language models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ahmed, Ahmed, Cooper, A. Feder, Koyejo, Sanmi, Liang, Percy
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Extracting memorized pieces of (copyrighted) books from open-weight language models
par: Cooper, A. Feder, et autres
Publié: (2025)

Reliable and Efficient Amortized Model-based Evaluation
par: Truong, Sang, et autres
Publié: (2025)

Why Do Safety Guardrails Degrade Across Languages?
par: Zhang, Max, et autres
Publié: (2026)

Logits are All We Need to Adapt Closed Models
par: Hiranandani, Gaurush, et autres
Publié: (2025)

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
par: Liu, Ken Ziyu, et autres
Publié: (2025)

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
par: Mo, Belinda, et autres
Publié: (2025)

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
par: Zhou, Zhanke, et autres
Publié: (2025)

ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment
par: Obbad, Elyas, et autres
Publié: (2024)

Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization
par: Chan, Willy, et autres
Publié: (2025)

Investigating Data Contamination for Pre-training Language Models
par: Jiang, Minhao, et autres
Publié: (2024)

Quantifying the Importance of Data Alignment in Downstream Model Performance
par: Chawla, Krrish, et autres
Publié: (2025)

UQ: Assessing Language Models on Unsolved Questions
par: Nie, Fan, et autres
Publié: (2025)

Between Randomness and Arbitrariness: Some Lessons for Reliable Machine Learning at Scale
par: Cooper, A. Feder
Publié: (2024)

Is Pre-training Truly Better Than Meta-Learning?
par: Miranda, Brando, et autres
Publié: (2023)

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
par: Schaeffer, Rylan, et autres
Publié: (2024)

Scalable Ensembling For Mitigating Reward Overoptimisation
par: Ahmed, Ahmed M., et autres
Publié: (2024)

Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data
par: Miranda, Brando, et autres
Publié: (2023)

Best-of-N Jailbreaking
par: Hughes, John, et autres
Publié: (2024)

On the Entropy Calibration of Language Models
par: Cao, Steven, et autres
Publié: (2025)

Fantastic Bugs and Where to Find Them in AI Benchmarks
par: Truong, Sang, et autres
Publié: (2025)

Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices
par: Tomita, Hikari, et autres
Publié: (2024)

SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas
par: Wei, Anjiang, et autres
Publié: (2025)

HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
par: Zhu, Junzhe, et autres
Publié: (2023)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States
par: Sun, Yu, et autres
Publié: (2024)

Estimating near-verbatim extraction risk in language models with decoding-constrained beam search
par: Cooper, A. Feder, et autres
Publié: (2026)

The language of time: a language model perspective on time-series foundation models
par: Xie, Yi, et autres
Publié: (2025)

Structured Prompts Improve Evaluation of Language Models
par: Aali, Asad, et autres
Publié: (2025)

GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification
par: Khamis, Ahmed Khaled
Publié: (2026)

Representation in large language models
par: Yetman, Cameron
Publié: (2025)

Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
par: Dubois, Yann, et autres
Publié: (2024)

SpecEval: Evaluating Model Adherence to Behavior Specifications
par: Ahmed, Ahmed, et autres
Publié: (2025)

Alignment faking in large language models
par: Greenblatt, Ryan, et autres
Publié: (2024)

Lightweight reranking for language model generations
par: Jain, Siddhartha, et autres
Publié: (2023)

Auditing language models for hidden objectives
par: Marks, Samuel, et autres
Publié: (2025)

Position: Model Collapse Does Not Mean What You Think
par: Schaeffer, Rylan, et autres
Publié: (2025)

Discovering Implicit Large Language Model Alignment Objectives
par: Chen, Edward, et autres
Publié: (2026)

The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior
par: Wang, Angelina, et autres
Publié: (2025)

Long-form factuality in large language models
par: Wei, Jerry, et autres
Publié: (2024)

Can large language models explore in-context?
par: Krishnamurthy, Akshay, et autres
Publié: (2024)

Peering Inside the Black Box: Uncovering LLM Errors in Optimization Modelling through Component-Level Evaluation
par: Refai, Dania, et autres
Publié: (2025)