Buchumschlag

Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Huang, Shih-Cheng, Li, Pin-Zu, Hsu, Yu-Chi, Chen, Kuang-Ming, Lin, Yu Tung, Hsiao, Shih-Kai, Tsai, Richard Tzong-Han, Lee, Hung-yi
Format:	Preprint
Veröffentlicht:	2023
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning
von: Huang, Chien-yu, et al.
Veröffentlicht: (2024)

InstructionCP: A fast approach to transfer Large Language Models into target language
von: Chen, Kuang-Ming, et al.
Veröffentlicht: (2024)

RNF43 Inactivation Enhances the B‐RAF/MEK Signaling and Creates a Combinatory Therapeutic Target in Cancer Cells
von: Shih‐Han Hsu, et al.
Veröffentlicht: (2024)

Systematic Analysis for Pretrained Language Model Priming for Parameter-Efficient Fine-tuning
von: Huang, Shih-Cheng, et al.
Veröffentlicht: (2022)

A$^2$TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation
von: Hsu, Sheng-Chi, et al.
Veröffentlicht: (2026)

Non-instructional Fine-tuning: Enabling Instruction-Following Capabilities in Pre-trained Language Models without Instruction-Following Data
von: Xie, Juncheng, et al.
Veröffentlicht: (2024)

Dosimetric evaluation and clinical application of collimated apertures with proton beam line scanning in stereotactic radiotherapy
von: Chen‐Yu Chou, et al.
Veröffentlicht: (2025)

Neuromodulation in Small Animal fMRI
von: Li‐Ming Hsu, et al.
Veröffentlicht: (2024)

Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors
von: Liang, Ren-Wei, et al.
Veröffentlicht: (2025)

Governing Sustainability Transitions Under Systemic Disruption: ESG‐Related Productivity Frictions and Structural Heterogeneity in Semiconductor Manufacturing
von: Shih‐Pin Chen, et al.
Veröffentlicht: (2026)

Prognostic Value of a Cardiopulmonary Exercise Testing‐Derived Summed Score in Idiopathic Pulmonary Fibrosis and Connective Tissue Disease‐Associated Interstitial Lung Disease: A Prospective Cohort Study
von: Yu‐Lin Tsai, et al.
Veröffentlicht: (2025)

Advanced Signal Analysis in Detecting Replay Attacks for Automatic Speaker Verification Systems
von: Kuang, Lee Shih
Veröffentlicht: (2024)

GSQA: An End-to-End Model for Generative Spoken Question Answering
von: Shih, Min-Han, et al.
Veröffentlicht: (2023)

SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition
von: Hsu, Ming-Hao, et al.
Veröffentlicht: (2024)

Utilizing collimated aperture with proton pencil beam scanning (PBS) for stereotactic radiotherapy
von: Chen‐Yu Chou, et al.
Veröffentlicht: (2024)

Circadian lighting effect for inpatients with schizophrenia: A prospective cohort study
von: Ya‐Chi Tsai, et al.
Veröffentlicht: (2024)

Examining the Effectiveness of the Approach of Visual Metaphor Instructional Design for Management Education: A Multi‐Aspect Theoretical View of Flow Experience and Perceived Task Value
von: Ying‐Lien Lin, et al.
Veröffentlicht: (2025)

Berry anthocyanins prevent α‐dicarbonyls and advanced glycation end product formation in phosphate‐buffered saline‐based model systems, cookie and ground pork
von: Yu‐Wen Hsiao, et al.
Veröffentlicht: (2024)

Warp-STAR: High-performance, Differentiable GPU-Accelerated Static Timing Analysis through Warp-oriented Parallel Orchestration
von: Huang, En-Ming, et al.
Veröffentlicht: (2026)

Perpetual Happiness
von: Tsai, Shih-shan Henry
Veröffentlicht: (2023)

ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
von: Hsiao, Chi-Yuan, et al.
Veröffentlicht: (2026)

Design and Implementation of a Secure RAG-Enhanced AI Chatbot for Smart Tourism Customer Service: Defending Against Prompt Injection Attacks -- A Case Study of Hsinchu, Taiwan
von: Shih, Yu-Kai, et al.
Veröffentlicht: (2025)

The Taiwan National Coordinated Early Psychosis Intervention Service: Comprehensive Overview and Early Outcomes
von: Yu‐Ju Shih, et al.
Veröffentlicht: (2025)

Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models
von: Lu, Ke-Han, et al.
Veröffentlicht: (2025)

Glutamate concentrations related to depression and mania symptoms in patients with Graves' disease: A 1H‐magnetic resonance spectroscopy study
von: Shih‐Hsien Lin, et al.
Veröffentlicht: (2024)

Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset
von: Hsu, Chih-Chung, et al.
Veröffentlicht: (2024)

Segment Anything, Even Occluded
von: Tai, Wei-En, et al.
Veröffentlicht: (2025)

R2SM: Referring and Reasoning for Selective Masks
von: Shih, Yu-Lin, et al.
Veröffentlicht: (2025)

Cascaded Transformer for Robust and Scalable SLA Decomposition via Amortized Optimization
von: Hsu, Cyril Shih-Huan
Veröffentlicht: (2026)

MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
von: Liang, Zhenwen, et al.
Veröffentlicht: (2024)

DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging
von: Lin, Tzu-Han, et al.
Veröffentlicht: (2024)

Temporal Hyperbolic Graph Representation Learning for Scale-Free Internet Routing and Delay Prediction
von: Kuo, Yi-Ling, et al.
Veröffentlicht: (2026)

ChatGPT As a Resource to Strengthen Mathematics Teaching and Learning: A Systematic Review
von: Chia Shih Su, et al.
Veröffentlicht: (2026)

MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2026)

Clonal dynamics of chronic myelomonocytic leukemia progression: paired‐sample comparison
von: Hsiao‐Wen Kao, et al.
Veröffentlicht: (2025)

From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2025)

Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
von: Thakkar, Megh, et al.
Veröffentlicht: (2024)

Site-Specific Color Features of Green Coffee Beans
von: Tan, Shu-Min, et al.
Veröffentlicht: (2024)

Simple 2D Convolutional Neural Network-based Approach for COVID-19 Detection
von: Hsu, Chih-Chung, et al.
Veröffentlicht: (2024)

Personal PM₂.₅ and HRV in Taiwan Amateur Runners data
von: Lee, Shih-Yu
Veröffentlicht: (2026)