Copertina

Multi-Trait Subspace Steering to Reveal the Dark Side of Human-AI Interaction

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chia, Xin Wei, Wong, Swee Liang, Pan, Jonathan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States
di: Chia, Xin Wei, et al.
Pubblicazione: (2025)

Enhancing Reasoning Capacity of SLM using Cognitive Enhancement
di: Pan, Jonathan, et al.
Pubblicazione: (2024)

Prompt Inject Detection with Generative Explanation as an Investigative Tool
di: Pan, Jonathan, et al.
Pubblicazione: (2025)

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
di: Jiang, Xinyan, et al.
Pubblicazione: (2025)

Exploring the Personality Traits of LLMs through Latent Features Steering
di: Yang, Shu, et al.
Pubblicazione: (2024)

Interactive Debugging and Steering of Multi-Agent AI Systems
di: Epperson, Will, et al.
Pubblicazione: (2025)

Mitigating Misalignment Contagion by Steering with Implicit Traits
di: Chang, Maria, et al.
Pubblicazione: (2026)

Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models
di: Berg, Cameron, et al.
Pubblicazione: (2026)

Inference-Time Policy Steering through Human Interactions
di: Wang, Yanwei, et al.
Pubblicazione: (2024)

Human-Centered Human-AI Interaction (HC-HAII): A Human-Centered AI Perspective
di: Xu, Wei
Pubblicazione: (2025)

OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation
di: Wu, Yichen, et al.
Pubblicazione: (2025)

BarrierSteer: LLM Safety via Learning Barrier Steering
di: Tran, Thanh Q., et al.
Pubblicazione: (2026)

Human-AI Interaction Design Standards
di: Zhao, Chaoyi, et al.
Pubblicazione: (2025)

PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration
di: Yu, Manjiang, et al.
Pubblicazione: (2025)

Revealed Multi-Objective Utility Aggregation in Human Driving
di: Sarkar, Atrisha, et al.
Pubblicazione: (2023)

Mixture-of-Subspaces in Low-Rank Adaptation
di: Wu, Taiqiang, et al.
Pubblicazione: (2024)

Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI Exploration
di: Woolley, Sandra, et al.
Pubblicazione: (2026)

The Dark Side of Digital Twins: Adversarial Attacks on AI-Driven Water Forecasting
di: Homaei, Mohammadhossein, et al.
Pubblicazione: (2025)

What Do You Mean? Exploring How Humans and AI Interact with Symbols and Meanings in Their Interactions
di: Habibi, Reza, et al.
Pubblicazione: (2025)

CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
di: Wang, Xintong, et al.
Pubblicazione: (2024)

On the Same Page: Dimensions of Perceived Shared Understanding in Human-AI Interaction
di: Liang, Qingyu, et al.
Pubblicazione: (2025)

Beyond Partner Diversity: An Influence-Based Team Steering Framework for Zero-Shot Human-Machine Teaming
di: Sheng, Wei, et al.
Pubblicazione: (2026)

Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition
di: Kazemitabaar, Majeed, et al.
Pubblicazione: (2024)

Adaptive Budget Allocation for Orthogonal-Subspace Adapter Tuning in LLMs Continual Learning
di: Wan, Zhiyi, et al.
Pubblicazione: (2025)

The Cognitive Circuit Breaker: A Systems Engineering Framework for Intrinsic AI Reliability
di: Pan, Jonathan
Pubblicazione: (2026)

Explainable Human-AI Interaction: A Planning Perspective
di: Sreedharan, Sarath, et al.
Pubblicazione: (2024)

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
di: Islam, Sekh Mainul, et al.
Pubblicazione: (2025)

Model Merging in the Essential Subspace
di: Li, Longhua, et al.
Pubblicazione: (2026)

The Dark Side of AI Transformers: Sentiment Polarization & the Loss of Business Neutrality by NLP Transformers
di: Kumar, Prasanna
Pubblicazione: (2026)

Exploring the Impact of Personality Traits on LLM Bias and Toxicity
di: Wang, Shuo, et al.
Pubblicazione: (2025)

Steering LLMs via Scalable Interactive Oversight
di: Zhou, Enyu, et al.
Pubblicazione: (2026)

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
di: Lv, Hang, et al.
Pubblicazione: (2025)

Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents
di: He, Muyu, et al.
Pubblicazione: (2025)

Harmful Traits of AI Companions
di: Knox, W. Bradley, et al.
Pubblicazione: (2025)

AI-exhibited Personality Traits Can Shape Human Self-concept through Conversations
di: Li, Jingshu, et al.
Pubblicazione: (2026)

The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs
di: Chen, Bocheng, et al.
Pubblicazione: (2024)

Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs
di: Chu, SeongYeub, et al.
Pubblicazione: (2024)

Revealing the Power of Masked Autoencoders in Traffic Forecasting
di: Sun, Jiarui, et al.
Pubblicazione: (2023)

Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education
di: Pan, Wei Hung, et al.
Pubblicazione: (2024)

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
di: Zhou, Xuhui, et al.
Pubblicazione: (2024)