Cover Image

Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ashkinaze, Joshua, Shen, Hua, Avula, Saipranav, Gilbert, Eric, Budak, Ceren
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment
by: Ashkinaze, Joshua, et al.
Published: (2024)

Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
by: Ashkinaze, Joshua, et al.
Published: (2024)

Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms
by: Ashkinaze, Joshua, et al.
Published: (2024)

The Dynamics of (Not) Unfollowing Misinformation Spreaders
by: Ashkinaze, Joshua, et al.
Published: (2024)

When People are Floods: Analyzing Dehumanizing Metaphors in Immigration Discourse with Large Language Models
by: Mendelsohn, Julia, et al.
Published: (2025)

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

Growth First, Care Second? Tracing the Landscape of LLM Value Preferences in Everyday Dilemmas
by: Chen, Zhiyi, et al.
Published: (2026)

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
by: Yao, Jing, et al.
Published: (2025)

Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories
by: Zhang, Yazhou, et al.
Published: (2025)

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
by: Jiang, Han, et al.
Published: (2024)

Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
by: Huang, Saffron, et al.
Published: (2025)

EigenBench: A Comparative Behavioral Measure of Value Alignment
by: Chang, Jonathn, et al.
Published: (2025)

ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models
by: Zhang, Zhaowei, et al.
Published: (2023)

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

Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
by: Duan, Shitong, et al.
Published: (2023)

Reward Models Inherit Value Biases from Pretraining
by: Christian, Brian, et al.
Published: (2026)

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
by: Lee, Jaehyeok, et al.
Published: (2026)

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
by: Jiang, Han, et al.
Published: (2025)

From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents
by: Qu, Jinxian, et al.
Published: (2026)

Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts
by: Zhang, Wenjing, et al.
Published: (2025)

Prompt Design Matters for Computational Social Science Tasks but in Unpredictable Ways
by: Atreja, Shubham, et al.
Published: (2024)

When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models
by: Venkata, Pruthvinath Jeripity
Published: (2026)

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

Information Suppression in Large Language Models: Auditing, Quantifying, and Characterizing Censorship in DeepSeek
by: Qiu, Peiran, et al.
Published: (2025)

ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
by: Shen, Hua, et al.
Published: (2024)

Temporal Preferences in Language Models for Long-Horizon Assistance
by: Mazyaki, Ali, et al.
Published: (2025)

DeepTutor: Towards Agentic Personalized Tutoring
by: Zhao, Bingxi, et al.
Published: (2026)

Minion: A Technology Probe to Explore How Users Negotiate Harmful Value Conflicts with AI Companions
by: Fan, Xianzhe, et al.
Published: (2024)

neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings
by: Ramamoorthy, Arnav, et al.
Published: (2025)

GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning
by: Yu, Jeffy, et al.
Published: (2024)

Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
by: Shen, Hua, et al.
Published: (2025)

ShaRP: Explaining Rankings and Preferences with Shapley Values
by: Pliatsika, Venetia, et al.
Published: (2024)

The Political Preferences of LLMs
by: Rozado, David
Published: (2024)

Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models
by: Jensen, Benjamin, et al.
Published: (2025)

Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights
by: Choi, Sooyung, et al.
Published: (2025)

Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation
by: Franceschelli, Giorgio, et al.
Published: (2025)

Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
by: Rakshit, Sushrita, et al.
Published: (2026)

Measuring Human Contribution in AI-Assisted Content Generation
by: Xie, Yueqi, et al.
Published: (2024)

Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation
by: Rasool, Abdur, et al.
Published: (2024)

DeepSurvey-Bench: Evaluating Academic Value of Automatically Generated Scientific Survey
by: Zhang, Guo-Biao, et al.
Published: (2026)