paper-with-me

홈 › Papers

Cultural Alignment in Large Language Models Using Soft Prompt Tuning

2025-03-20 · Reem I. Masoud, Martin Ferianc, Philip Treleaven, Miguel Rodrigues

Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. These methods typically require labeled or preference datasets and involve updating model weights to align the LLM with the training objective or reward model. Meanwhile, in social sciences such as cross-cultural studies, factor analysis is widely used to uncover underlying dimensions or latent variables that explain observed patterns in survey data. The non-differentiable nature of these measurements deriving from survey data renders the former alignment methods infeasible for alignment with cultural dimensions. To overcome this, we propose a parameter efficient strategy that combines soft prompt tuning, which freezes the model parameters while modifying the input prompt embeddings, with Differential Evolution (DE), a black-box optimization method for cases where a differentiable objective is unattainable. This strategy ensures alignment consistency without the need for preference data or model parameter updates, significantly enhancing efficiency and mitigating overfitting. Our method demonstrates significant improvements in LLama-3-8B-Instruct's cultural dimensions across multiple regions, outperforming both the Naive LLM and the In-context Learning (ICL) baseline, and effectively bridges computational models with human cultural nuances.

📄 PDF Abstract BibTeX arXiv:2503.16094

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningLarge Language ModelSurvey

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting

2025-12-10 · James Luther, Donald Brown arxiv

Culture is a core component of human-to-human interaction and plays a vital role in how we perceive and interact with others. Advancements in the effectiveness of Large Language Models (LLMs) in generating human-sounding…

Prompt Programming for Cultural Bias and Alignment of Large Language Models

2026-03-17 · Maksim Eren, Eric Michalak, Brian Cook, Johnny Seales arxiv

Culture shapes reasoning, values, prioritization, and strategic decision-making, yet large language models (LLMs) often exhibit cultural biases that misalign with target populations. As LLMs are increasingly used for str…

Prompt Engineering

The American Ghost in the Machine: How language models align culturally and the effects of cultural prompting

2025-12-13 · James Luther, Donald Brown arxiv

Culture is the bedrock of human interaction; it dictates how we perceive and respond to everyday interactions. As the field of human-computer interaction grows via the rise of generative Large Language Models (LLMs), the…

Cultural Bias and Cultural Alignment of Large Language Models

2023-11-23 · Yan Tao, Olga Viberg, Ryan S. Baker, Rene F. Kizilcec

Culture fundamentally shapes people's reasoning, behavior, and communication. As people increasingly use generative artificial intelligence (AI) to expedite and automate personal and professional tasks, cultural values e…

AlignCultura: Towards Culturally Aligned Large Language Models?

2026-04-21 · Gautam Siddharth Kashyap, Mark Dras, Usman Naseem arxiv

Cultural alignment in Large Language Models (LLMs) is essential for producing contextually aware, respectful, and trustworthy outputs. Without it, models risk generating stereotyped, insensitive, or misleading responses …

Response Generation