A Scoping Review of Sycophancy in Large Language Models: Operational and Theoretical Recognition

As large language models (LLMs) usage grows across different domains, sycophancy, the tendency for output to align with users, is increasingly being recognized as a primary issue arising from applying LLMs into critical areas. Current research has provided a variety of theoretical definitions, mitigation techniques, and quantification for sycophancy. However, there is little to no consistency across different papers. This scoping review seeks to connect different works on LLM sycophancy by identifying themes in theoretical definitions, measurement methods, and inducement techniques of sycophancy. By analyzing 26 papers (preprints, conference proceedings, and journal articles) from arXiv, ACL Anthology, and Scopus, this review has found that currently, LLM sycophancy is being recognized more as an operational tradeoff than manipulation done through flattery. Additionally, this review has found that researchers generally opt to induce sycophancy through a combination of user-authority framing and user-preference signaling. This review provides a standardized taxonomy for research procedures which creates a stronger foundation for future LLM research to be more cross-compatible.