Image de couverture de livre

Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yao, Jing, Yi, Xiaoyuan, Duan, Shitong, Wang, Jindong, Bai, Yuzhuo, Huang, Muhua, Zhang, Peng, Lu, Tun, Dou, Zhicheng, Sun, Maosong, Xie, Xing
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
par: Yao, Jing, et autres
Publié: (2025)

IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization
par: Bai, Yuzhuo, et autres
Publié: (2025)

Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning
par: Duan, Shitong, et autres
Publié: (2023)

CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization
par: Yao, Jing, et autres
Publié: (2025)

On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
par: Huang, Muhua, et autres
Publié: (2025)

CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
par: Yao, Jing, et autres
Publié: (2024)

Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights
par: Choi, Sooyung, et autres
Publié: (2025)

Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches
par: Biedma, Pablo, et autres
Publié: (2024)

The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment
par: Kim, HyunJin, et autres
Publié: (2024)

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
par: Lee, Jaehyeok, et autres
Publié: (2026)

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
par: Guo, Hanze, et autres
Publié: (2025)

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
par: Duan, Shitong, et autres
Publié: (2024)

On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
par: Wang, Xinpeng, et autres
Publié: (2024)

MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions
par: Zhu, Yanxu, et autres
Publié: (2025)

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
par: Jiang, Han, et autres
Publié: (2025)

Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs
par: Ma, Huanhuan, et autres
Publié: (2025)

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
par: Tan, Bryan Chen Zhengyu, et autres
Publié: (2026)

Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization
par: Wang, Xingqi, et autres
Publié: (2024)

MoVa: Towards Generalizable Classification of Human Morals and Values
par: Chen, Ziyu, et autres
Publié: (2025)

ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
par: Shen, Hua, et autres
Publié: (2024)

DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes
par: Cheng, Jiehan, et autres
Publié: (2025)

Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization
par: Kim, HyunJin, et autres
Publié: (2025)

LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output
par: Karinshak, Elise, et autres
Publié: (2024)

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
par: Zhang, Xiangxu, et autres
Publié: (2026)

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
par: Shen, Guobin, et autres
Publié: (2025)

AI Evaluation Should Require Standardized Item-Level Data Releases
par: Jiang, Han, et autres
Publié: (2026)

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
par: Jiang, Han, et autres
Publié: (2024)

Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents
par: Zhang, Hanzhong, et autres
Publié: (2025)

CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution
par: Cao, Maosong, et autres
Publié: (2024)

OpenCompass: A Universal Evaluation Platform for Large Language Models
par: Cao, Maosong, et autres
Publié: (2026)

Beyond Benchmark: LLMs Evaluation with an Anthropomorphic and Value-oriented Roadmap
par: Wang, Jun, et autres
Publié: (2025)

Spatio-Temporal Autoregressions for High Dimensional Matrix-Valued Time Series
par: Dou, Baojun, et autres
Publié: (2025)

The Transmission Value of Energy Storage and Fundamental Limitations
par: Zhang, Qian, et autres
Publié: (2024)

SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization
par: Hu, Xixu, et autres
Publié: (2024)

Flames: Benchmarking Value Alignment of LLMs in Chinese
par: Huang, Kexin, et autres
Publié: (2023)

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
par: Bai, Yuzhuo, et autres
Publié: (2026)

Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
par: Dong, Haonan, et autres
Publié: (2026)

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
par: Bai, Xuehai, et autres
Publié: (2026)

STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking
par: Shen, Sicheng, et autres
Publié: (2025)

Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
par: Röttger, Paul, et autres
Publié: (2024)