Copertina

Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kang, Yipeng, Wang, Junqi, Li, Yexin, Wang, Mengmeng, Tu, Wenming, Wang, Quansen, Li, Hengli, Wu, Tingjun, Feng, Xue, Zhong, Fangwei, Zheng, Zilong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models
di: Zhang, Junyu, et al.
Pubblicazione: (2026)

BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
di: Li, Hengli, et al.
Pubblicazione: (2025)

PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
di: Zhang, Zhaowei, et al.
Pubblicazione: (2025)

The AI Hippocampus: How Far are We From Human Memory?
di: Jia, Zixia, et al.
Pubblicazione: (2026)

Simple Role Assignment is Extraordinarily Effective for Safety Alignment
di: Ziheng, Zhou, et al.
Pubblicazione: (2026)

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
di: Li, Jiaqi, et al.
Pubblicazione: (2025)

Discrete Markov Bridge
di: Li, Hengli, et al.
Pubblicazione: (2025)

LooGLE: Can Long-Context Language Models Understand Long Contexts?
di: Li, Jiaqi, et al.
Pubblicazione: (2023)

UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models
di: Tu, Wenming, et al.
Pubblicazione: (2025)

Are LLMs Smarter Than Chimpanzees? An Evaluation on Perspective Taking and Knowledge State Estimation
di: Yang, Dingyi, et al.
Pubblicazione: (2026)

RAM: Towards an Ever-Improving Memory System by Learning from Communications
di: Li, Jiaqi, et al.
Pubblicazione: (2024)

Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
di: Zhong, Li, et al.
Pubblicazione: (2024)

MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation
di: Qiu, Shuwen, et al.
Pubblicazione: (2023)

Synergistic Bearing Effect and Failure Mechanism of Backfill–Coal Pillar Composite Structure
di: Guangtao Wang, et al.
Pubblicazione: (2026)

Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation
di: Zhong, Li, et al.
Pubblicazione: (2023)

Simulating Human-like Daily Activities with Desire-driven Autonomy
di: Wang, Yiding, et al.
Pubblicazione: (2024)

Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL
di: Cheng, Ning, et al.
Pubblicazione: (2024)

Reinforced Context Order Recovery for Adaptive Reasoning and Planning
di: Ma, Long, et al.
Pubblicazione: (2025)

RosePO: Aligning LLM-based Recommenders with Human Values
di: Liao, Jiayi, et al.
Pubblicazione: (2024)

In-situ Value-aligned Human-Robot Interactions with Physical Constraints
di: Li, Hongtao, et al.
Pubblicazione: (2025)

AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models
di: Yang, Jialiang, et al.
Pubblicazione: (2026)

Can Post-Training Transform LLMs into Causal Reasoners?
di: Chen, Junqi, et al.
Pubblicazione: (2026)

ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making
di: Luo, Yitong, et al.
Pubblicazione: (2025)

Clinical Inspired MRI Lesion Segmentation
di: Yan, Lijun, et al.
Pubblicazione: (2025)

CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning
di: Li, Yexin
Pubblicazione: (2025)

Refined blow up criteria for the full compressible Navier-Stokes equations involving temperature
di: Jiu, Quansen, et al.
Pubblicazione: (2019)

Local well-posedness of strong solutions to the 2D nonhomogeneous primitive equations with density-dependent viscosity
di: Jiu, Quansen, et al.
Pubblicazione: (2024)

Global existence and uniqueness of strong solutions to the 2D nonhomogeneous primitive equations with density-dependent viscosity
di: Jiu, Quansen, et al.
Pubblicazione: (2024)

Credibility Governance: A Social Mechanism for Collective Self-Correction under Weak Truth Signals
di: He, Wanying, et al.
Pubblicazione: (2026)

A Study on the Ancient theater of official house in The Taihang mountain area of North Henan Province in China
di: Hengli Peng
Pubblicazione: (2023)

Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
di: Wang, Jiahao, et al.
Pubblicazione: (2025)

Aligning MLLM Benchmark With Human Preferences via Structural Equation Modeling
di: Xiong, Shengwu., et al.
Pubblicazione: (2025)

A longitudinal dyadic analysis of gender ideology during the transition into parenthood
di: Yexin Zheng, et al.
Pubblicazione: (2025)

Phononically shielded multi-wavelength photonic-crystal membrane for cavity quantum optomechanics
di: Li, Hanbing, et al.
Pubblicazione: (2024)

Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation
di: Wang, Yuanfei, et al.
Pubblicazione: (2025)

Near-Optimal Quantum Algorithms for Computing (Coarse) Correlated Equilibria of General-Sum Games
di: Li, Tongyang, et al.
Pubblicazione: (2025)

Premarital Cohabitation and Intimate Partner Violence in Urban China: Evidence From Beijing
di: Yexin Zheng, et al.
Pubblicazione: (2026)

CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games
di: Xu, Shuhang, et al.
Pubblicazione: (2025)

Diffusion‐Optimized Long Lifespan 4.6 V LiCoO2: Homogenizing Cycled Bulk‐To‐Surface Li Concentration with Reduced Structure Stress
di: Kang Wu, et al.
Pubblicazione: (2024)

Aligning Human Motion Generation with Human Perceptions
di: Wang, Haoru, et al.
Pubblicazione: (2024)