Hongyu Lin, Ben He, Xianpei Han, Yingfei Sun, Le Sun, Xiaoyang Chen, Boxi Cao, Tianshu Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
The practice of Retrieval-Augmented Generation (RAG), which integrates Large Language Models (LLMs) with retrieval systems, has become increasingly prevalent. However, the repercussions of LLM-derived content infiltrating the web and influencing the retrievalgeneration feedback loop are largely uncharted territories. In this study, we construct and iteratively run a simulation pipeline to deeply investigate the short-term and long-term effects of LLM text on RAG systems. Taking the trending Open Domain Question Answering (ODQA) task as a point of entry, our findings reveal a potential digital "Spiral of Silence" effect, with LLM-generated text consistently outperforming human-authored content in search rankings, thereby diminishing the presence and impact of human contributions online. This trend risks creating an imbalanced information ecosystem, where the unchecked proliferation of erroneous LLM-generated content may result in the marginalization of accurate information. We urge the academic community to take heed of this potential issue, ensuring a diverse and authentic digital information landscape. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2404.10496")
get_code_for_paper("2404.10496")
have("2404.10496")
Connect an agent — have() is free.