Copertina

Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Xinyue, Mireshghallah, Niloofar, Ginsburg, Jane C., Chakrabarty, Tuhin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Computers and Society
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers
di: Chakrabarty, Tuhin, et al.
Pubblicazione: (2025)

Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers
di: Chakrabarty, Tuhin, et al.
Pubblicazione: (2023)

ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
di: Chen, Tong, et al.
Pubblicazione: (2025)

Developing Story: Case Studies of Generative AI's Use in Journalism
di: Brigham, Natalie Grace, et al.
Pubblicazione: (2024)

Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits
di: Chakrabarty, Tuhin, et al.
Pubblicazione: (2024)

AI Safety Should Prioritize the Future of Work
di: Hazra, Sanchaita, et al.
Pubblicazione: (2025)

Can Good Writing Be Generative? Expert-Level AI Writing Emerges through Fine-Tuning on High-Quality Books
di: Chakrabarty, Tuhin, et al.
Pubblicazione: (2026)

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
di: Xu, Naen, et al.
Pubblicazione: (2025)

SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning
di: Xu, Tianyang, et al.
Pubblicazione: (2025)

Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs
di: Zhang, Renfei, et al.
Pubblicazione: (2025)

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

Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
di: Pang, Xianghe, et al.
Pubblicazione: (2024)

Position: Privacy Is Not Just Memorization!
di: Mireshghallah, Niloofar, et al.
Pubblicazione: (2025)

Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
di: Sakhawat, Adib, et al.
Pubblicazione: (2026)

Art or Artifice? Large Language Models and the False Promise of Creativity
di: Chakrabarty, Tuhin, et al.
Pubblicazione: (2023)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models
di: Anwar, Usman, et al.
Pubblicazione: (2024)

Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models
di: Raiyan, Syed Rifat
Pubblicazione: (2026)

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
di: Liu, Xiaoze, et al.
Pubblicazione: (2024)

Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
di: Greco, Candida M., et al.
Pubblicazione: (2026)

Whack-a-Chip: The Futility of Hardware-Centric Export Controls
di: Gupta, Ritwik, et al.
Pubblicazione: (2024)

LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models
di: Meadows, Gwenyth Isobel, et al.
Pubblicazione: (2024)

How to Stop Playing Whack-a-Mole: Mapping the Ecosystem of Technologies Facilitating AI-Generated Non-Consensual Intimate Images
di: Ding, Michelle L., et al.
Pubblicazione: (2026)

On the Creativity of Large Language Models
di: Franceschelli, Giorgio, et al.
Pubblicazione: (2023)

Contextual StereoSet: Stress-Testing Bias Alignment Robustness in Large Language Models
di: Basu, Abhinaba, et al.
Pubblicazione: (2026)

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

In Silico Sociology: Forecasting COVID-19 Polarization with Large Language Models
di: Kozlowski, Austin C., et al.
Pubblicazione: (2024)

AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation
di: Chakrabarty, Tuhin, et al.
Pubblicazione: (2025)

Cross-Language Bias Examination in Large Language Models
di: Liang, Yuxuan, et al.
Pubblicazione: (2025)

Differentially Private Learning Needs Better Model Initialization and Self-Distillation
di: Ngong, Ivoline C., et al.
Pubblicazione: (2024)

Investigating Cultural Alignment of Large Language Models
di: AlKhamissi, Badr, et al.
Pubblicazione: (2024)

Large Language Models Develop Novel Social Biases Through Adaptive Exploration
di: Wu, Addison J., et al.
Pubblicazione: (2025)

LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
di: Frisch, Ivar, et al.
Pubblicazione: (2024)

Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
di: Dahl, Matthew, et al.
Pubblicazione: (2024)

Evaluating Large Language Models for Detecting Antisemitism
di: Patel, Jay, et al.
Pubblicazione: (2025)

Anticipating Innovation Using Large Language Models
di: Fenoaltea, Enrico Maria, et al.
Pubblicazione: (2026)

Open-Ended Wargames with Large Language Models
di: Hogan, Daniel P., et al.
Pubblicazione: (2024)

Large Language Models for Education: A Survey
di: Xu, Hanyi, et al.
Pubblicazione: (2024)

How Large Language Models are Designed to Hallucinate
di: Ackermann, Richard, et al.
Pubblicazione: (2025)

Large Language Models as Misleading Assistants in Conversation
di: Hou, Betty Li, et al.
Pubblicazione: (2024)

Evaluating Psychological Safety of Large Language Models
di: Li, Xingxuan, et al.
Pubblicazione: (2022)