Imagen de Portada

Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Rushi, Liu, Jiateng, Qian, Cheng, Shen, Yifan, Pan, Yanzhou, Xu, Zhaozhuo, Abbasi, Ahmed, Ji, Heng, Zhang, Denghui
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
por: Zhang, Guangwei, et al.
Publicado: (2025)

Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents
por: Liu, Jiateng, et al.
Publicado: (2026)

Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
por: Wu, Yuheng, et al.
Publicado: (2025)

Do LLMs Know to Respect Copyright Notice?
por: Xu, Jialiang, et al.
Publicado: (2024)

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
por: Wu, Yuheng, et al.
Publicado: (2025)

Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks
por: Zhang, Guangwei, et al.
Publicado: (2026)

Atomic Reasoning for Scientific Table Claim Verification
por: Zhang, Yuji, et al.
Publicado: (2025)

Monadic Context Engineering
por: Zhang, Yifan, et al.
Publicado: (2025)

Measuring Copyright Risks of Large Language Model via Partial Information Probing
por: Zhao, Weijie, et al.
Publicado: (2024)

Automating Financial Statement Audits with Large Language Models
por: Wang, Rushi, et al.
Publicado: (2025)

Language Steering for Multilingual In-Context Learning
por: Kirtane, Neeraja, et al.
Publicado: (2026)

Context Engineering 2.0: The Context of Context Engineering
por: Hua, Qishuo, et al.
Publicado: (2025)

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation
por: Sun, Chenkai, et al.
Publicado: (2025)

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
por: Gu, Zhuohan, et al.
Publicado: (2024)

Context Steering: Controllable Personalization at Inference Time
por: He, Jerry Zhi-Yang, et al.
Publicado: (2024)

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
por: Li, Mufei, et al.
Publicado: (2025)

Conversational Context Classification: A Representation Engineering Approach
por: Pan, Jonathan
Publicado: (2026)

Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering
por: Zhu, Jiachen, et al.
Publicado: (2026)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
por: Liu, Zheyuan, et al.
Publicado: (2025)

Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
por: Banayeeanzade, Amin, et al.
Publicado: (2025)

EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
por: Liu, Jiateng, et al.
Publicado: (2024)

OSExpert: Computer-Use Agents Learning Professional Skills via Exploration
por: Liu, Jiateng, et al.
Publicado: (2026)

Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering
por: Ong, Kenneth J. K., et al.
Publicado: (2025)

COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation
por: Sahay, Kenji, et al.
Publicado: (2025)

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
por: Zhang, Qizheng, et al.
Publicado: (2025)

LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion
por: Ling, Zhan, et al.
Publicado: (2025)

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
por: Han, Peixuan, et al.
Publicado: (2025)

OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation
por: Zhang, Hanning, et al.
Publicado: (2025)

A Global Context Mechanism for Sequence Labeling
por: Xu, Conglei, et al.
Publicado: (2023)

SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation
por: Lv, Hang, et al.
Publicado: (2026)

Rethinking Visual Neglect: Steering via Context-Preference for MLLM Hallucination Mitigation
por: Wu, Jingwen, et al.
Publicado: (2026)

ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation
por: Pan, Yanzhou, et al.
Publicado: (2025)

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
por: Sharma, Kartik, et al.
Publicado: (2026)

Understanding Emergent In-Context Learning from a Kernel Regression Perspective
por: Han, Chi, et al.
Publicado: (2023)

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
por: Shen, Jingyan, et al.
Publicado: (2025)

Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
por: Zhang, Yong, et al.
Publicado: (2025)

Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission
por: Ye, Jiangnan, et al.
Publicado: (2026)

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
por: Li, Jiaqian, et al.
Publicado: (2026)

Local and Global Contexts for Conversation
por: Lin, Zuoquan, et al.
Publicado: (2024)

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
por: Bigelow, Eric, et al.
Publicado: (2025)