Copertina

Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kelley, Sean W., Riedl, Christoph
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Affective Computing Has Changed: The Foundation Model Disruption
di: Schuller, Björn, et al.
Pubblicazione: (2024)

PAD: Personalized Alignment of LLMs at Decoding-Time
di: Chen, Ruizhe, et al.
Pubblicazione: (2024)

Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment
di: Pustejovsky, James, et al.
Pubblicazione: (2026)

Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation
di: Wen, Zhiyuan, et al.
Pubblicazione: (2024)

When LLMs Team Up: The Emergence of Collaborative Affective Computing
di: Lai, Wenna, et al.
Pubblicazione: (2025)

LLMs with Personalities in Multi-issue Negotiation Games
di: Noh, Sean, et al.
Pubblicazione: (2024)

Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
di: Agarwal, Utkarsh, et al.
Pubblicazione: (2024)

CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions
di: Kim, Tae Soo, et al.
Pubblicazione: (2025)

Can LLMs Truly Embody Human Personality? Analyzing AI and Human Behavior Alignment in Dispute Resolution
di: Kwon, Deuksin, et al.
Pubblicazione: (2026)

On Prompt Sensitivity of ChatGPT in Affective Computing
di: Amin, Mostafa M., et al.
Pubblicazione: (2024)

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
di: Kim, Jinhwa, et al.
Pubblicazione: (2025)

Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery
di: Clark, Nicholas, et al.
Pubblicazione: (2025)

Echoes of Automation: The Increasing Use of LLMs in Newsmaking
di: Ansari, Abolfazl, et al.
Pubblicazione: (2025)

Orchestrating LLMs with Different Personalizations
di: Zhou, Jin Peng, et al.
Pubblicazione: (2024)

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics
di: Lee, Seungbeen, et al.
Pubblicazione: (2024)

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
di: Sun, Zhongxiang, et al.
Pubblicazione: (2026)

Behavior Trees Enable Structured Programming of Language Model Agents
di: Kelley, Richard
Pubblicazione: (2024)

Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects
di: Peng, Ji-Lun, et al.
Pubblicazione: (2026)

Persona-Aware Alignment Framework for Personalized Dialogue Generation
di: Li, Guanrong, et al.
Pubblicazione: (2025)

DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
di: Yao, Bingsheng, et al.
Pubblicazione: (2025)

Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
di: Cheng, Myra, et al.
Pubblicazione: (2026)

REAL: Response Embedding-based Alignment for LLMs
di: Zhang, Honggen, et al.
Pubblicazione: (2024)

Fake Alignment: Are LLMs Really Aligned Well?
di: Wang, Yixu, et al.
Pubblicazione: (2023)

Flames: Benchmarking Value Alignment of LLMs in Chinese
di: Huang, Kexin, et al.
Pubblicazione: (2023)

From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization
di: Wang, Zehong, et al.
Pubblicazione: (2025)

What Has Been Lost with Synthetic Evaluation?
di: Gill, Alexander, et al.
Pubblicazione: (2025)

Multimodality and Attention Increase Alignment in Natural Language Prediction Between Humans and Computational Models
di: Kewenig, Viktor, et al.
Pubblicazione: (2023)

Optimizing Alignment with Less: Leveraging Data Augmentation for Personalized Evaluation
di: Seraj, Javad, et al.
Pubblicazione: (2024)

Multi-Personality Generation of LLMs at Decoding-time
di: Chen, Rongxin, et al.
Pubblicazione: (2025)

Guided Profile Generation Improves Personalization with LLMs
di: Zhang, Jiarui
Pubblicazione: (2024)

Advancing and Benchmarking Personalized Tool Invocation for LLMs
di: Huang, Xu, et al.
Pubblicazione: (2025)

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
di: Sun, Lihao, et al.
Pubblicazione: (2025)

Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematurity
di: Zhao, Shuai, et al.
Pubblicazione: (2025)

Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
di: Clymer, Joshua, et al.
Pubblicazione: (2024)

Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
di: Chehade, Mohamad, et al.
Pubblicazione: (2025)

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
di: Zhang, Haoke, et al.
Pubblicazione: (2025)

Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges
di: Thakur, Aman Singh, et al.
Pubblicazione: (2024)

Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment
di: Cai, Wenrui, et al.
Pubblicazione: (2025)

One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment
di: Cai, Hongru, et al.
Pubblicazione: (2026)

TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment
di: Nguyen, Thi-Nhung, et al.
Pubblicazione: (2026)