arXiv AI
VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 8
VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
arXiv:2602. 03160v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles.
Hugging Face Trending Papers
Jul 9
PLURAL: A Global Dataset for Value Alignment
Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS), a nationally representative survey spanning 92 countries.
arXiv AI
Jul 10
PLURAL: A Global Dataset for Value Alignment
arXiv:2607. 08034v1 Announce Type: cross Abstract: Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems.
arXiv Computation and Language
Sep 21
Cultural Alignment in Large Language Models Using Soft Prompt Tuning
The paper proposes a method for culturally aligning large language models (LLMs) using soft prompt tuning optimized via Differential Evolution (DE). Unlike traditional fine‑tuning or reinforcement learning, this approach keeps model weights frozen and requires no preference data, instead leveraging aggregated survey scores from Hofstede's Value Survey Module (VSM13). Experiments on four countries and four instruction‑tuned models show that DE‑optimized prompts reduce cultural discrepancy, improve agreement with the World Values Survey, and are preferred in blinded pairwise evaluations by LLM judges.
arXiv AI
Aug 25
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
The paper investigates how preference tuning—optimizing language models with explicit preference signals—behaves when applied to new domains. It systematically compares five alignment objectives and several adaptation strategies, such as target‑domain supervised fine‑tuning and pseudo‑labeling, across summarization, question‑answering helpfulness, and safety tasks. Results show that while pseudo‑labeling reduces domain‑shift degradation, it also causes mode collapse, highlighting a trade‑off between generalization and diversity.
Hugging Face Trending Papers
Aug 25
Preference Data Selection for Mitigating the Alignment Tax in Large Language Models
Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastrophic forgetting of pre-trained general capabilit...