Can Memory-Augmented LLM Agents Aid Journalism in Interpreting and Framing News for Diverse Audiences?

TL;DR

This paper introduces MADES, an agent-based framework that simulates societal communication to identify and address comprehension gaps in news articles for diverse audiences, enhancing understanding through targeted supplementary material.

Contribution

The paper presents MADES, a novel agent-based framework that models societal news discussion to detect misunderstandings and improve comprehension for various audience segments.

Findings

Agents effectively identify comprehension gaps in news content.

Supplementary materials significantly improve agents' understanding.

Framework validated through statistical and human evaluations.

Abstract

Modern news is often comprehensive, weaving together information from diverse domains, including technology, finance, and agriculture. This very comprehensiveness creates a challenge for interpretation, as audiences typically possess specialized knowledge related to their expertise, age, or standpoint. Consequently, a reader might fully understand the financial implications of a story but fail to grasp or even actively misunderstand its legal or technological dimensions, resulting in critical comprehension gaps. In this work, we investigate how to identify these comprehension gaps and provide solutions to improve audiences' understanding of news content, particularly in the aspects of articles outside their primary domains of knowledge. We propose MADES, an agent-based framework designed to simulate societal communication. The framework utilizes diverse agents, each configured to represent a specific occupation or age group. Each agent is equipped with a memory system. These agents are then simulated to discuss the news. This process enables us to monitor and analyze their behavior and cognitive processes. Our findings indicate that the framework can identify confusions and misunderstandings within news content through its iterative discussion process. Based on these accurate identifications, the framework then designs supplementary material. We validated these outcomes using both statistical analysis and human evaluation, and the results show that agents exhibit significantly improved news understanding after receiving this supplementary material.