Copertina

Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Lechen, Zhou, Yusheng, Ergen, Tolga, Logeswaran, Lajanugen, Lee, Moontae, Jurgens, David
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Human-Computer Interaction Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SPRIG: Improving Large Language Model Performance by System Prompt Optimization
di: Zhang, Lechen, et al.
Pubblicazione: (2024)

When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models
di: Zheng, Mingqian, et al.
Pubblicazione: (2023)

Evaluating the Prompt Steerability of Large Language Models
di: Miehling, Erik, et al.
Pubblicazione: (2024)

Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework
di: Chakraborty, Mohna, et al.
Pubblicazione: (2025)

You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments
di: Shu, Bangzhao, et al.
Pubblicazione: (2023)

Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue
di: Ivey, Jonathan, et al.
Pubblicazione: (2024)

Digital Diasporas: How Origin Characteristics and Host-Native Distance Shape Immigrants' Online Cultural Retention
di: Khatua, Aparup, et al.
Pubblicazione: (2025)

Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts
di: Song, Yunpeng, et al.
Pubblicazione: (2024)

MapExplorer: New Content Generation from Low-Dimensional Visualizations
di: Zhang, Xingjian, et al.
Pubblicazione: (2024)

Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior
di: Lee, Minjae, et al.
Pubblicazione: (2025)

ViseGPT: Towards Better Alignment of LLM-generated Data Wrangling Scripts and User Prompts
di: Zhu, Jiajun, et al.
Pubblicazione: (2025)

Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability
di: Lia, Nusrat Jahan, et al.
Pubblicazione: (2026)

Towards Dataset-scale and Feature-oriented Evaluation of Text Summarization in Large Language Model Prompts
di: Lee, Sam Yu-Te, et al.
Pubblicazione: (2024)

Towards Emotion Co-regulation with LLM-powered Socially Assistive Robots: Integrating LLM Prompts and Robotic Behaviors to Support Parent-Neurodivergent Child Dyads
di: Li, Jing, et al.
Pubblicazione: (2025)

SteerEval: A Framework for Evaluating Steerability with Natural Language Profiles for Recommendation
di: Zhou, Joyce, et al.
Pubblicazione: (2026)

Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs
di: Sun, Huaman, et al.
Pubblicazione: (2023)

Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?
di: Shen, Siqi, et al.
Pubblicazione: (2025)

Towards Holistic Prompt Craft
di: Lindley, Joseph, et al.
Pubblicazione: (2025)

The Impact of Generative AI on Social Media: An Experimental Study
di: Møller, Anders Giovanni, et al.
Pubblicazione: (2025)

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
di: Qi, Jirui, et al.
Pubblicazione: (2023)

People Can Accurately Predict Behavior of Complex Algorithms That Are Available, Compact, and Aligned
di: Popowski, Lindsay, et al.
Pubblicazione: (2026)

Who Reaps All the Superchats? A Large-Scale Analysis of Income Inequality in Virtual YouTuber Livestreaming
di: Zhao, Ruijing, et al.
Pubblicazione: (2025)

Modeling Pedestrian Crossing Behavior: A Reinforcement Learning Approach with Sensory Motor Constraints
di: Wang, Yueyang, et al.
Pubblicazione: (2024)

CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applications
di: Chen, Chaoran, et al.
Pubblicazione: (2024)

Can Code Outlove Blood? An LLM-based VR Experience to Prompt Reflection on Parental Verbal Abuse
di: Fu, Jiaying, et al.
Pubblicazione: (2025)

CultiVerse: Towards Cross-Cultural Understanding for Paintings with Large Language Model
di: Zhang, Wei, et al.
Pubblicazione: (2024)

Cross-Domain Transfer Learning Method for Thermal Adaptive Behavior Recognition with WiFi
di: Lv, Zhaohe, et al.
Pubblicazione: (2024)

Can Large Language Model Agents Simulate Human Trust Behavior?
di: Xie, Chengxing, et al.
Pubblicazione: (2024)

CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming
di: Feng, Li, et al.
Pubblicazione: (2023)

Stayin' Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data
di: Gebreegziabher, Simret Araya, et al.
Pubblicazione: (2026)

Steerable Chatbots: Personalizing LLMs with Preference-Based Activation Steering
di: Bo, Jessica Y., et al.
Pubblicazione: (2025)

Behavioral Indicators of Overreliance During Interaction with Conversational Language Models
di: Liu, Chang, et al.
Pubblicazione: (2026)

Bloom: Designing for LLM-Augmented Behavior Change Interactions
di: Jörke, Matthew, et al.
Pubblicazione: (2025)

Prompting Destiny: Negotiating Socialization and Growth in an LLM-Mediated Speculative Gameworld
di: Yang, Mandi, et al.
Pubblicazione: (2026)

Exploring Similarity between Neural and LLM Trajectories in Language Processing
di: Xiao, Xin, et al.
Pubblicazione: (2025)

PromptAid: Prompt Exploration, Perturbation, Testing and Iteration using Visual Analytics for Large Language Models
di: Mishra, Aditi, et al.
Pubblicazione: (2023)

Analysis of Distracted Pedestrians Crossing Behavior: An Immersive Virtual Reality Application
di: Sulle, Methusela, et al.
Pubblicazione: (2025)

Towards Sustainable Creativity Support: An Exploratory Study on Prompt Based Image Generation
di: Paludan, Daniel Hove, et al.
Pubblicazione: (2025)

Model Behavior Specification by Leveraging LLM Self-Playing and Self-Improving
di: Park, Soya, et al.
Pubblicazione: (2025)

GazeSummary: Exploring Gaze as an Implicit Prompt for Personalization in Text-based LLM Tasks
di: Ding, Jiexin, et al.
Pubblicazione: (2026)