INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models

2024-12-16

arXiv.org

AI Summary

Current large language models (LLMs) operate as passive learners, relying solely on static pretraining data and lacking capabilities for active questioning and iterative knowledge refinement. Method: We propose a teacher-student LLM dialogue-driven interactive learning paradigm and introduce the first scalable, question-answering–driven adaptive concept transfer framework. It enables cold-start models to match static baseline performance within five interaction rounds across 1,347 diverse multimodal contexts—including news articles, academic papers, song lyrics, movie plots, and images—while mitigating bottlenecks induced by weak teacher models. The method leverages structured inter-LLM dialogues and integrates heterogeneous, multi-source information modeling. Contribution/Results: Extensive experiments demonstrate up to 25% absolute performance gain across diverse model architectures and downstream tasks, significantly improving knowledge acquisition efficiency, generalization, and robustness.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Large language models (LLMs) excel at answering questions but remain passive learners-absorbing static data without the ability to question and refine knowledge. This paper explores how LLMs can transition to interactive, question-driven learning through student-teacher dialogues. We introduce INTERACT (INTERactive learning for Adaptive Concept Transfer), a framework in which a"student"LLM engages a"teacher"LLM through iterative inquiries to acquire knowledge across 1,347 contexts, including song lyrics, news articles, movie plots, academic papers, and images. Our experiments show that across a wide range of scenarios and LLM architectures, interactive learning consistently enhances performance, achieving up to a 25% improvement, with 'cold-start' student models matching static learning baselines in as few as five dialogue turns. Interactive setups can also mitigate the disadvantages of weaker teachers, showcasing the robustness of question-driven learning.

Problem

• Enabling interactive learning in large language models
• Transitioning from passive to question-driven knowledge refinement
• Improving performance through student-teacher dialogue frameworks

Innovation

• Interactive student-teacher dialogue framework
• Adaptive knowledge transfer across contexts
• Question-driven learning enhances model performance