# EchoTrace: Diagnosing Recursive Risks in LLM-Powered Recommender Systems

arXiv: https://arxiv.org/abs/2602.07442 · HTML: https://mlsanity.com/paper/2602.07442/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2026.

## Built on by (most cited first, 1 of 1)

- [Rethinking Fairness in LLM-Based Recommender Systems: A Survey](https://mlsanity.com/paper/2606.28340/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly integrated into recommender systems as data augmenters, profile generators, and recommendation modules. While these roles can enhance semantic understanding and recommendation quality, they also introduce LLM-specific risks such as bias and hallucination. These risks become more critical in feedback-loop settings, where LLM-generated signals and recommendations recursively shape future training data and recommendation dynamics. In this paper, we propose a role-aware, phase-wise diagnostic framework for analyzing how LLM-induced risks emerge, propagate, and accumulate in LLM-powered recommender systems. Our framework combines controlled feedback-loop simulation with longitudinal phase-wise diagnosis across LLM-generated content, recommendation outputs, feedback-loop dynamics, and ecosystem-level effects. Experiments on widely used benchmarks show that LLM-based components can amplify popularity bias, introduce spurious signals through hallucination, and gradually produce polarized and self-reinforcing exposure patterns over time. The code for EchoTrace is available at https://github.com/DongUk-Park/EchoTrace.