Who Does This Name Remind You of ? Nationality Prediction via Large Language Model Associative Memory

2026-01-19

AI Summary

This work addresses the limitations of conventional prompting methods in effectively leveraging cultural and historical knowledge embedded within large language models (LLMs) for name-based nationality prediction. To overcome this, the authors propose LAMA, a novel framework that reconceptualizes LLMs as associative memory systems. LAMA employs two collaborative agents—a Person Agent and a Media Agent—to associate input names with relevant public figures, enabling indirect reasoning through a voting mechanism, conditional completion, and a Top-K nationality aggregation strategy. This approach departs from direct prompting paradigms and achieves 81.7% accuracy on a 99-country nationality prediction task, significantly outperforming existing prompting techniques and neural network models. Notably, LAMA demonstrates enhanced robustness for low-frequency nationalities, where data scarcity typically hinders performance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Prompt Engineering / Prompting
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large language models (LLMs) possess extensive world knowledge, yet methods for effectively eliciting this knowledge remain underexplored. Nationality and region prediction tasks require understanding of not only linguistic features but also cultural and historical background, making LLM world knowledge particularly valuable. However, conventional LLM prompting methods rely on direct reasoning approaches, which have limitations in applying abstract linguistic rules. We propose LLM Associative Memory Agents (LAMA), a novel framework that leverages LLM world knowledge as associative memory. Rather than directly inferring nationality from names, LAMA recalls famous individuals with the same name and aggregates their nationalities through indirect reasoning. A dual-agent architecture comprising a Person Agent and a Media Agent, specialized in different knowledge domains, recalls famous individuals in parallel, generating Top-1 predictions through voting and Top-K predictions through conditional completion. On a 99-country nationality prediction task, LAMA achieved 0.817 accuracy, substantially outperforming conventional LLM prompting methods and neural models. Our experiments reveal that LLMs exhibit higher reliability in recalling concrete examples than in abstract reasoning, that recall-based approaches are robust to low-frequency nationalities independent of data frequency distributions, and that the dual-agent architecture functions complementarily to produce synergistic effects. These results demonstrate the effectiveness of a new multi-agent system that retrieves and aggregates LLM knowledge rather than prompting reasoning.

Problem

• nationality prediction
• large language models
• associative memory
• name-based inference
• world knowledge

Innovation

• associative memory
• large language models
• multi-agent system
• nationality prediction
• indirect reasoning