Saved in:
Bibliographic Details
Main Authors: Kendapadi, Aum, Zaman, Kerem, Menon, Rakesh R., Srivastava, Shashank
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.11388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915316393574400
author Kendapadi, Aum
Zaman, Kerem
Menon, Rakesh R.
Srivastava, Shashank
author_facet Kendapadi, Aum
Zaman, Kerem
Menon, Rakesh R.
Srivastava, Shashank
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11388
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models
Kendapadi, Aum
Zaman, Kerem
Menon, Rakesh R.
Srivastava, Shashank
Computation and Language
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.
title INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2412.11388