Buchumschlag

Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Tagliabue, Valen, Dung, Leonard
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?
von: Dung, Leonard, et al.
Veröffentlicht: (2025)

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
von: Wiedermann-Möller, Jonas, et al.
Veröffentlicht: (2026)

Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
von: Tagliabue, Jacopo, et al.
Veröffentlicht: (2025)

Probing Persona-Dependent Preferences in Language Models
von: Gilg, Oscar, et al.
Veröffentlicht: (2026)

Querying Everything Everywhere All at Once: Supervaluationism for the Agentic Lakehouse
von: Tagliabue, Jacopo
Veröffentlicht: (2026)

AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators
von: Tagliabue, Jacopo
Veröffentlicht: (2025)

Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governance
von: Tagliabue, Jacopo, et al.
Veröffentlicht: (2025)

Against racing to AGI: Cooperation, deterrence, and catastrophic risks
von: Dung, Leonard, et al.
Veröffentlicht: (2025)

Misalignment or misuse? The AGI alignment tradeoff
von: Hellrigel-Holderbaum, Max, et al.
Veröffentlicht: (2025)

Calibrating Verbalized Probabilities for Large Language Models
von: Wang, Cheng, et al.
Veröffentlicht: (2024)

Aligning Large Language Model Behavior with Human Citation Preferences
von: Ando, Kenichiro, et al.
Veröffentlicht: (2026)

How does Misinformation Affect Large Language Model Behaviors and Preferences?
von: Peng, Miao, et al.
Veröffentlicht: (2025)

Subjective Behaviors and Preferences in LLM: Language of Browsing
von: Sundaresan, Sai, et al.
Veröffentlicht: (2025)

Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing
von: Ulmer, Dennis, et al.
Veröffentlicht: (2025)

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
von: Zhu, Jian-Qiao, et al.
Veröffentlicht: (2025)

Initial Risk Probing and Feasibility Testing of Glow: a Generative AI-Powered Dialectical Behavior Therapy Skills Coach for Substance Use Recovery and HIV Prevention
von: Wang, Liying, et al.
Veröffentlicht: (2026)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
von: Wang, Libo
Veröffentlicht: (2024)

Dynamic Welfare-Maximizing Pooled Testing
von: Lopez, Nicholas, et al.
Veröffentlicht: (2026)

ConfTuner: Training Large Language Models to Express Their Confidence Verbally
von: Li, Yibo, et al.
Veröffentlicht: (2025)

Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience
von: Bärmann, Leonard, et al.
Veröffentlicht: (2024)

Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture
von: Lu, Hong, et al.
Veröffentlicht: (2025)

Taking AI Welfare Seriously
von: Long, Robert, et al.
Veröffentlicht: (2024)

Are we Doomed to an AI Race? Why Self-Interest Could Drive Countries Towards a Moratorium on Superintelligence
von: Roussel, Edward, et al.
Veröffentlicht: (2026)

Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
von: Schulhoff, Sander, et al.
Veröffentlicht: (2023)

Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models
von: Bärmann, Leonard, et al.
Veröffentlicht: (2023)

Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier
von: Badrinath, Anirudhan, et al.
Veröffentlicht: (2024)

Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
von: Chen, Hao-Yuan
Veröffentlicht: (2026)

Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models
von: Erden, Zeki Doruk, et al.
Veröffentlicht: (2025)

LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
von: Shen, Tiesunlong, et al.
Veröffentlicht: (2026)

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
von: Ni, Jingwei, et al.
Veröffentlicht: (2025)

Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning
von: Clark, Jaden, et al.
Veröffentlicht: (2025)

A Tool for Generating Exceptional Behavior Tests With Large Language Models
von: Zhong, Linghan, et al.
Veröffentlicht: (2025)

exLong: Generating Exceptional Behavior Tests with Large Language Models
von: Zhang, Jiyang, et al.
Veröffentlicht: (2024)

Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision
von: Jang, Chaeyun, et al.
Veröffentlicht: (2025)

ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models
von: Wu, Zixuan, et al.
Veröffentlicht: (2025)

Boosting Self-Efficacy and Performance of Large Language Models via Verbal Efficacy Stimulations
von: Chen, Rui, et al.
Veröffentlicht: (2025)

On Diversified Preferences of Large Language Model Alignment
von: Zeng, Dun, et al.
Veröffentlicht: (2023)

Measuring Political Preferences in AI Systems: An Integrative Approach
von: Rozado, David
Veröffentlicht: (2025)

Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planning
von: Abugurain, Mohammed, et al.
Veröffentlicht: (2024)

Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
von: Kour, George, et al.
Veröffentlicht: (2025)