Cover Image

Turning Language Model Training from Black Box into a Sandbox

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pope, Nicolas, Tedre, Matti
Format:	Preprint
Published:	2026
Subjects:	Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

An Educational Tool for Learning about Social Media Tracking, Profiling, and Recommendation
by: Pope, Nicolas, et al.
Published: (2024)

Classroom Activities and New Classroom Apps for Enhancing Children's Understanding of Social Media Mechanisms
by: Vartiainen, Henriikka, et al.
Published: (2025)

Breakable Machine: A K-12 Classroom Game for Transformative AI Literacy Through Spoofing and eXplainable AI (XAI)
by: Hilke, Olli, et al.
Published: (2025)

An XAI Social Media Platform for Teaching K-12 Students AI-Driven Profiling, Clustering, and Engagement-Based Recommending
by: Pope, Nicolas, et al.
Published: (2024)

Infrastructure, Human Capacity, and High Hopes: A Decade of Development of e-Learning in a Tanzanian HEI
by: Matti Tedre
Published: (2010)

The Sandbox Configurator: A Framework to Support Technical Assessment in AI Regulatory Sandboxes
by: Buscemi, Alessio, et al.
Published: (2025)

Trustworthiness in Stochastic Systems: Towards Opening the Black Box
by: Chien, Jennifer, et al.
Published: (2025)

The Ethics of LLM Sandbox and Persona Dynamics
by: Gebbie, Tim, et al.
Published: (2026)

The Bathtub of European AI Governance: Identifying Technical Sandboxes as the Micro-Foundation of Regulatory Learning
by: Deckenbrunnen, Tom, et al.
Published: (2026)

Digital Agriculture Sandbox for Collaborative Research
by: Zafar, Osama, et al.
Published: (2025)

Decoding the Black Box: Discerning AI Rhetorics About and Through Poetic Prompting
by: Edgar, P. D., et al.
Published: (2025)

Brokerage in the Black Box: Swing States, Strategic Ambiguity, and the Global Politics of AI Governance
by: Tran, Ha-Chi
Published: (2026)

Public Discourse Sandbox: Facilitating Human and AI Digital Communication Research
by: Radivojevic, Kristina, et al.
Published: (2025)

Mysterious and Manipulative Black Boxes: A Qualitative Analysis of Perceptions on Recommender Systems
by: Ruohonen, Jukka
Published: (2023)

Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement
by: Kersting, Nicholas S., et al.
Published: (2026)

Black-Box Access is Insufficient for Rigorous AI Audits
by: Casper, Stephen, et al.
Published: (2024)

Inside the Black Box: Detecting and Mitigating Algorithmic Bias across Racialized Groups in College Student-Success Prediction
by: Gándara, Denisa, et al.
Published: (2023)

All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
by: Takemoto, Kazuhiro
Published: (2024)

Leveraging Imperfect Sources to Detect Fairwashing in Black-Box Auditing
by: Bourrée, Jade Garcia, et al.
Published: (2023)

Unlocking the Black Box: Analysing the EU Artificial Intelligence Act's Framework for Explainability in AI
by: Pavlidis, Georgios
Published: (2025)

Operationalising AI Regulatory Sandboxes under the EU AI Act: The Triple Challenge of Capacity, Coordination and Attractiveness to Providers
by: Ahern, Deirdre
Published: (2025)

Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs
by: Hartmann, David, et al.
Published: (2026)

Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing
by: Xian, Ruicheng, et al.
Published: (2025)

From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy
by: Zabolotnii, Serhii, et al.
Published: (2026)

Simulating counterfactuals
by: Karvanen, Juha, et al.
Published: (2023)

Explain the Black Box for the Sake of Science: the Scientific Method in the Era of Generative Artificial Intelligence
by: Mengaldo, Gianmarco
Published: (2024)

If there's a Trigger Warning, then where's the Trigger? Investigating Trigger Warnings at the Passage Level
by: Wiegmann, Matti, et al.
Published: (2024)

Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning
by: Yao, Fangzhou, et al.
Published: (2026)

What Do LLMs Associate with Your Name? A Human-Centered Black-Box Audit of Personal Data
by: Staufer, Dimitri, et al.
Published: (2026)

Black Box Absorption: LLMs Undermining Innovative Ideas
by: Cao, Wenjun
Published: (2025)

Training Diffusion Language Models for Black-Box Optimization
by: Sun, Zipeng, et al.
Published: (2026)

A Multi-Turn Framework for Evaluating AI Misuse in Fraud and Cybercrime Scenarios
by: Mai, Kimberly T., et al.
Published: (2026)

A Relational (Re)Turn: Revisit Interactive Art through Interaction and Aesthetics
by: Zhou, Aven-Le
Published: (2025)

PersLLM: A Personified Training Approach for Large Language Models
by: Zeng, Zheni, et al.
Published: (2024)

A Taxonomy of Stereotype Content in Large Language Models
by: Nicolas, Gandalf, et al.
Published: (2024)

"What Is It That You Don't Understand?" Language Games and Black Box Algorithms
by: Demichelis, Remy
Published: (2026)

Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
by: Kiet, Huynh Trung, et al.
Published: (2026)

Design and Implementation of a Psychiatry Resident Training System Based on Large Language Models
by: Zhong, Zhenguang, et al.
Published: (2025)

A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction
by: Lincoln, Nicole, et al.
Published: (2026)

White-Box Sensitivity Auditing with Steering Vectors
by: Cyberey, Hannah, et al.
Published: (2026)