Image de couverture de livre

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Le, Linh, Williams-King, David, Merzouk, Mohamed Amine, Kamanda, Aton, Oberman, Adam
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence I.2.7
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
par: Williams-King, David, et autres
Publié: (2025)

SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions
par: Pan, Huitong, et autres
Publié: (2024)

Behavioural Analysis of Alignment Faking
par: Hadida, Nathaniel Mitrani, et autres
Publié: (2026)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
par: Saji, Alan, et autres
Publié: (2025)

IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMs
par: Manikantan, Kawshik, et autres
Publié: (2024)

Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment
par: Su, Ruoxi, et autres
Publié: (2026)

Large Language Models as Oracles for Ontology Alignment
par: Lushnei, Sviatoslav, et autres
Publié: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
par: Peters, Sydney, et autres
Publié: (2025)

Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
par: Kim, San, et autres
Publié: (2024)

Latent Planning Emerges with Scale
par: Hanna, Michael, et autres
Publié: (2026)

A dataset of questions on decision-theoretic reasoning in Newcomb-like problems
par: Oesterheld, Caspar, et autres
Publié: (2024)

Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs
par: Tytarenko, Stepan, et autres
Publié: (2024)

ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
par: Chang, Jiale, et autres
Publié: (2026)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
par: Fadli, Samih
Publié: (2025)

RLM-on-KG: Heuristics First, LLMs When Needed: Adaptive Retrieval Control over Mention Graphs for Scattered Evidence
par: Volpini, Andrea, et autres
Publié: (2026)

xInv: Explainable Optimization of Inverse Problems
par: Memery, Sean, et autres
Publié: (2025)

Uncovering Latent Human Wellbeing in Language Model Embeddings
par: Freire, Pedro, et autres
Publié: (2024)

Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously
par: Adiletta, Andrew, et autres
Publié: (2025)

PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI
par: Mukhopadhyay, Srija, et autres
Publié: (2025)

Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment
par: Li, Shanghao, et autres
Publié: (2025)

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars
par: Hua, Yuncheng, et autres
Publié: (2025)

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams
par: Llorente-Saguer, Isaac
Publié: (2026)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
par: Oketunji, Abiodun Finbarrs
Publié: (2023)

Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning
par: Cacioli, Jon-Paul
Publié: (2026)

SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation
par: Hua, Yuncheng, et autres
Publié: (2025)

ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning
par: Chang, Edward Y., et autres
Publié: (2025)

Evaluating Steering Techniques using Human Similarity Judgments
par: Studdiford, Zach, et autres
Publié: (2025)

Unlocking the Wisdom of Large Language Models: An Introduction to The Path to Artificial General Intelligence
par: Chang, Edward Y.
Publié: (2024)

Reasoning-Based AI for Startup Evaluation (R.A.I.S.E.): A Memory-Augmented, Multi-Step Decision Framework
par: Preuveneers, Jack, et autres
Publié: (2025)

Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment
par: Wang, Liang, et autres
Publié: (2026)

RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion
par: Niu, Guanglin, et autres
Publié: (2026)

Quantifying Self-Preservation Bias in Large Language Models
par: Migliarini, Matteo, et autres
Publié: (2026)

Evaluating Relational Reasoning in LLMs with REL
par: Fesser, Lukas, et autres
Publié: (2026)

KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
par: Parashar, Jayant, et autres
Publié: (2026)

RAudit: A Blind Auditing Protocol for Large Language Model Reasoning
par: Chang, Edward Y., et autres
Publié: (2026)

Towards ethical multimodal systems
par: Roger, Alexis, et autres
Publié: (2023)

AI-Powered Annotation Pipelines for Stabilizing Large Language Models: A Human-AI Synergy Approach
par: Pathak, Gangesh, et autres
Publié: (2025)

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance
par: Ivanov, Igor
Publié: (2025)

ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
par: Fang, Bowen, et autres
Publié: (2026)

PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
par: Pulipaka, Sidharth, et autres
Publié: (2026)