Copertina

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Lihao, Yan, Lewen, Lu, Xiaoya, Lee, Andrew, Zhang, Jie, Shao, Jing
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Computers and Society
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Language-based Valence and Arousal Expressions between the United States and China: a Cross-Cultural Examination
di: Cho, Young-Min, et al.
Pubblicazione: (2024)

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

Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms
di: Sun, Yuxi, et al.
Pubblicazione: (2025)

LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations
di: Solopova, Veronika, et al.
Pubblicazione: (2026)

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

From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs
di: Chen, Ruxiao, et al.
Pubblicazione: (2025)

I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
di: Campedelli, Gian Maria, et al.
Pubblicazione: (2024)

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

MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network
di: Ahire, Vrushank, et al.
Pubblicazione: (2025)

ELEPHANT: Measuring and understanding social sycophancy in LLMs
di: Cheng, Myra, et al.
Pubblicazione: (2025)

RvB: Automating AI System Hardening via Iterative Red-Blue Games
di: Huang, Lige, et al.
Pubblicazione: (2026)

Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game
di: Dong, Ruiqi, et al.
Pubblicazione: (2024)

XCR-Bench: A Multi-Task Benchmark for Evaluating Cultural Reasoning in LLMs
di: Kabir, Mohsinul, et al.
Pubblicazione: (2026)

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability
di: Lu, Xiaoya, et al.
Pubblicazione: (2025)

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

Beyond Vision: How Large Language Models Interpret Facial Expressions from Valence-Arousal Values
di: Mehra, Vaibhav, et al.
Pubblicazione: (2025)

The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
di: Han, Pengrui, et al.
Pubblicazione: (2025)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
di: Gao, Cheng, et al.
Pubblicazione: (2025)

Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives
di: Haider, Batool, et al.
Pubblicazione: (2025)

Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
di: Wang, Bing, et al.
Pubblicazione: (2026)

Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings
di: Radzikowski, Jakub, et al.
Pubblicazione: (2026)

PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations
di: Li, Jiatong, et al.
Pubblicazione: (2024)

Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models
di: Shin, Jisu, et al.
Pubblicazione: (2024)

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
di: Wang, Peisong, et al.
Pubblicazione: (2025)

HugAgent: Benchmarking LLMs for Simulation of Individualized Human Reasoning
di: Li, Chance Jiajie, et al.
Pubblicazione: (2025)

Expressing Social Emotions: Misalignment Between LLMs and Human Cultural Emotion Norms
di: Bhattacharyya, Sree, et al.
Pubblicazione: (2026)

Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts
di: Wang, Xing, et al.
Pubblicazione: (2025)

Assessing the Performance of Human-Capable LLMs -- Are LLMs Coming for Your Job?
di: Mavi, John, et al.
Pubblicazione: (2024)

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

Reinforcing Stereotypes of Anger: Emotion AI on African American Vernacular English
di: Dorn, Rebecca, et al.
Pubblicazione: (2025)

The simulation of judgment in LLMs
di: Loru, Edoardo, et al.
Pubblicazione: (2025)

Measuring Teaching with LLMs
di: Hardy, Michael
Pubblicazione: (2025)

The Political Preferences of LLMs
di: Rozado, David
Pubblicazione: (2024)

Towards Algorithmic Fidelity: Mental Health Representation across Demographics in Synthetic vs. Human-generated Data
di: Mori, Shinka, et al.
Pubblicazione: (2024)

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs
di: de Landa, Joseba Fernandez, et al.
Pubblicazione: (2026)

AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
di: Gu, Zhouhong, et al.
Pubblicazione: (2024)

Medical Malice: A Dataset for Context-Aware Safety in Healthcare LLMs
di: D'addario, Andrew Maranhão Ventura
Pubblicazione: (2025)

Profiling learners' affective engagement: Emotion AI, intercultural pragmatics, and language learning
di: Godwin-Jones, Robert
Pubblicazione: (2026)

ZPD-SCA: Unveiling the Blind Spots of LLMs in Assessing Students' Cognitive Abilities
di: Dong, Wenhan, et al.
Pubblicazione: (2025)

Moral Mazes in the Era of LLMs
di: Nguyen, Dang, et al.
Pubblicazione: (2026)