The Information Efficiency Metric (IEM): An Info-Metric Approach for Quantifying AI Language Model Performance

Read full text Summarise with VIRAT
Authors: Ljerka Luić, Maja Barbić, Marijana Rončević
Cited by: 0
References: 38

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The interaction between humans and artificial intelligence has become a critical channel for information exchange, yet no quantitative, theoretically grounded framework exists for measuring information efficiency in human–AI communication. This study empirically validated an info-metrics framework operationalizing information efficiency through three dimensions—information density (D), relevance (R), and redundancy (Q)—synthesized into an information efficiency metric (IEM). We analyzed 60 AI responses from ChatGPT 5.2 and Claude Opus 4.5 across factual, analytical, and creative question types using combined coding, automated structural measures, and human evaluation of informational units. The results showed that information density and relevance positively contributed to IEM, while redundancy had a negative contribution. Efficiency varied by task type, with factual prompts showing the highest variability across models and highest efficiency. Contrary to expectations, creative responses did not exhibit higher redundancy, suggesting that expressive diversity does not necessarily constitute informational noise. The framework offers a task-sensitive, theoretically grounded approach to evaluating human–AI information exchange beyond correctness or subjective quality judgment, supporting systems-oriented optimization of conversational AI protocols.

Fields of Study & Subjects

Topic Modeling Information Retrieval and Search Behavior Speech and dialogue systems

Publication details

Journal / source
Information
Volume
17
Issue
3
Pages
307–307
Publication date
22 March 2026
Language
EN