# Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection

arXiv: https://arxiv.org/abs/2602.23123 · HTML: https://mlsanity.com/paper/2602.23123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [The science of fake news](https://mlsanity.com/paper/2307.07903/) (2023)
- [Prompt-Based Editing for Text Style Transfer](https://mlsanity.com/paper/2301.11997/) (2023)
- [The Readability of Tweets and their Geographic Correlation with Education](https://mlsanity.com/paper/1401.6058/) (2014)

## Abstract (arXiv)

In the attention economy, sensational content exposes consumers to excessive emotional stimulation, hindering calm decision-making. This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide. The Emotion Analysis Agent quantifies stimulus intensity using a 6-emotion BERT classifier, and the Emotion Adjustment Agent rewrites texts into two presentation modes, BALANCED (neutralized text) and COOL (neutralized text + supplementary text), using an LLM. The Balance Monitoring Agent aggregates weekly information consumption patterns and generates personalized advice, while the Personal Guide Agent recommends a presentation mode according to consumer sensitivity. Experiments on 800 AG News articles demonstrated significant stimulus score reduction (up to 19.3%) and improved emotion balance while maintaining semantic preservation. Near-zero correlation between stimulus reduction and semantic preservation confirmed that the two are independently controllable. Category-level analysis revealed substantial reduction (17.8-33.8%) in Sports, Business, and Sci/Tech, whereas the effect was limited in the World category, where facts themselves are inherently high-stimulus. The proposed system provides a framework for supporting calm information reception of consumers without restricting access to the original text.