Improving Behavioral Alignment in LLM Social Simulations via Context Formation and Navigation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kong, Letian, Qianran, Jin, Zhang, Renyu
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

Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space
di: Fu, Xingcheng, et al.
Pubblicazione: (2026)

Online Context Learning for Socially Compliant Navigation
di: Okunevich, Iaroslav, et al.
Pubblicazione: (2024)

OpenNav: Open-World Navigation with Multimodal Large Language Models
di: Yuan, Mingfeng, et al.
Pubblicazione: (2025)

Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts
di: Weller, Niklas, et al.
Pubblicazione: (2026)

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

Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
di: Mooney, James, et al.
Pubblicazione: (2025)

Bridging Social Psychology and LLM Reasoning: Conflict-Aware Meta-Review Generation via Cognitive Alignment
di: Chen, Wei, et al.
Pubblicazione: (2025)

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
di: Zhang, Hongbin, et al.
Pubblicazione: (2025)

Intrinsic-Motivation Multi-Robot Social Formation Navigation with Coordinated Exploration
di: Fu, Hao, et al.
Pubblicazione: (2025)

Improving LLM Group Fairness on Tabular Data via In-Context Learning
di: Cherepanova, Valeriia, et al.
Pubblicazione: (2024)

A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog
di: Wei, Ding
Pubblicazione: (2026)

Societal Alignment Frameworks Can Improve LLM Alignment
di: Stańczak, Karolina, et al.
Pubblicazione: (2025)

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
di: Zhang, Yuheng, et al.
Pubblicazione: (2025)

Less is More: Improving LLM Alignment via Preference Data Selection
di: Deng, Xun, et al.
Pubblicazione: (2025)

In-Context Imitation Learning via Next-Token Prediction
di: Fu, Letian, et al.
Pubblicazione: (2024)

InFact: Informativeness Alignment for Improved LLM Factuality
di: Cohen, Roi, et al.
Pubblicazione: (2025)

SeLaR: Selective Latent Reasoning in Large Language Models
di: Fu, Renyu, et al.
Pubblicazione: (2026)

Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting
di: Zhang, Lizhe, et al.
Pubblicazione: (2025)

Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
di: Pang, Xianghe, et al.
Pubblicazione: (2024)

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
di: Zhou, Siyu, et al.
Pubblicazione: (2024)

Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
di: Li, Xiaozhe, et al.
Pubblicazione: (2026)

RTMol: Rethinking Molecule-text Alignment in a Round-trip View
di: Chen, Letian, et al.
Pubblicazione: (2025)

VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
di: Chen, Jiawei, et al.
Pubblicazione: (2026)

Goal Alignment in LLM-Based User Simulators for Conversational AI
di: Mehri, Shuhaib, et al.
Pubblicazione: (2025)

Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
di: Shen, Sicheng, et al.
Pubblicazione: (2026)

The Price of Format: Diversity Collapse in LLMs
di: Yun, Longfei, et al.
Pubblicazione: (2025)

Improving Safety Alignment via Balanced Direct Preference Optimization
di: Zhao, Shiji, et al.
Pubblicazione: (2026)

EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation
di: Liu, Yi, et al.
Pubblicazione: (2026)

Efficient Knowledge Infusion via KG-LLM Alignment
di: Jiang, Zhouyu, et al.
Pubblicazione: (2024)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
di: Wang, Yanbo, et al.
Pubblicazione: (2026)

LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment
di: Li, Shipeng, et al.
Pubblicazione: (2025)

BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
di: Xu, Wenda, et al.
Pubblicazione: (2024)

CMOMgen: Complex Multi-Ontology Alignment via Pattern-Guided In-Context Learning
di: Silva, Marta Contreiras, et al.
Pubblicazione: (2025)

Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents
di: Han, Bin, et al.
Pubblicazione: (2026)

SEAR: A Multimodal Dataset for Analyzing AR-LLM-Driven Social Engineering Behaviors
di: Yu, Tianlong, et al.
Pubblicazione: (2025)

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks
di: Ozaki, Yusuke, et al.
Pubblicazione: (2026)

Enhancing Retrieval Augmentation via Adversarial Collaboration
di: Zhang, Letian, et al.
Pubblicazione: (2025)

LLM-Agent-based Social Simulation for Attitude Diffusion
di: Reji, Deepak John
Pubblicazione: (2026)

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
di: Zhao, Hongjue, et al.
Pubblicazione: (2026)

Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation
di: Jiang, Jiuyun, et al.
Pubblicazione: (2026)