Headlines You Won't Forget: Can Pronoun Insertion Increase Memorability?

2026-04-21

AI Summary

This study investigates whether inserting first- and second-person pronouns into news headlines enhances memory retention and evaluates the feasibility of large language models (LLMs) automatically inserting such pronouns while preserving core semantics. Drawing on the direct address effect from cognitive psychology and leveraging LLM-based text rewriting, the authors conduct three controlled memory experiments involving 240 participants to systematically analyze the impact of pronoun insertion on memorability. Results reveal a mixed effect: pronoun inclusion influences memory differentially depending on headline topic, insertion strategy, and local context. Furthermore, LLM-generated versions frequently exhibit deviations in factual accuracy, emotional tone preservation, or linguistic naturalness. This work represents the first integration of the direct address effect with controllable LLM text generation, offering a novel perspective on automatic, memorability-oriented text optimization.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• 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
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

For news headlines to influence beliefs and drive action, relevant information needs to be retained and retrievable from memory. In this probing study we draw on experiment designs from cognitive psychology to examine how a specific linguistic feature, namely direct address through first- and second-person pronouns, affects memorability and to what extent it is feasible to use large language models for the targeted insertion of such a feature into existing text without changing its core meaning. Across three controlled memorization experiments with a total of 240 participants, yielding 7,680 unique memory judgments, we show that pronoun insertion has mixed effects on memorability. Exploratory analyses indicate that effects differ based on headline topic, how pronouns are inserted and their immediate contexts. Additional data and fine-grained analysis is needed to draw definitive conclusions on these mediating factors. We further show that automatic revisions by LLMs are not always appropriate: Crowdsourced evaluations find many of them to be lacking in content accuracy and emotion retention or resulting in unnatural writing style. We make our collected data available for future work.

Problem

• memorability
• pronoun insertion
• news headlines
• large language models
• direct address

Innovation

• pronoun insertion
• memorability
• large language models
• direct address
• controlled memory experiments