Cultural Alignment in Large Language Models Using Soft Prompt Tuning

arXiv:2503.16094 · cs.CL · Submitted 2025-03-20 · Read on arXiv

cs.CL

Submitted: 2025-03-20

Updated: 2026-09-18

Code: https://github.com/lm-sys/FastChat

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 50× in this paper · explained in 1 episode
• Accuracy — 13× in this paper · explained in 1 episode
• Large Language Model — 13× in this paper
• Saudi Arabia — 11× in this paper
• Embeddings — 8× in this paper · explained in 2 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Alignment Methods — 4× in this paper · explained in 1 episode
• Differential Evolution — 4× in this paper
• In-Context Learning — 3× in this paper · explained in 4 episodes
• Loss Function — 3× in this paper · explained in 2 episodes
• Adaptability — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Direct Preference Optimization — 2× in this paper
• Generalization — 2× in this paper · explained in 13 episodes
• In-Context Learning (ICL) — 2× in this paper · explained in 5 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Objective Function — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• World Values Survey — 2× in this paper
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Power Distance Index — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Uncertainty Avoidance Index — 1× in this paper
• United Stated — 1× in this paper

Sources

• PersianLLaMA: Towards Building First Persian Large Language Model
• COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
• AceGPT, Localizing Large Language Models in Arabic
• Theoretical guarantees on the best-of-n alignment policy
• Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages
• The Power of Scale for Parameter-Efficient Prompt Tuning
• Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
• Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions
• CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming
• Controlled Decoding from Language Models
• SeaLLMs -- Large Language Models for Southeast Asia
• A Survey on In-context Learning
• Towards Measuring the Representation of Subjective Global Opinions in Language Models
• Survey of Cultural Awareness in Language Models: Text and Beyond
• A Roadmap to Pluralistic Alignment
• Cultural Bias and Cultural Alignment of Large Language Models
• Loss Functions and Metrics in Deep Learning
• UCCIX: Irish-eXcellence Large Language Model
• HyperCLOVA X Technical Report
• Group Preference Optimization: Few-Shot Alignment of Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering