arXiv Open Access 2025

Sycophancy Claims about Language Models: The Missing Human-in-the-Loop

Jan Batzner Volker Stocker Stefan Schmid Gjergji Kasneci

Lihat Sumber

Abstrak

Sycophantic response patterns in Large Language Models (LLMs) have been increasingly claimed in the literature. We review methodological challenges in measuring LLM sycophancy and identify five core operationalizations. Despite sycophancy being inherently human-centric, current research does not evaluate human perception. Our analysis highlights the difficulties in distinguishing sycophantic responses from related concepts in AI alignment and offers actionable recommendations for future research.

Topik & Kata Kunci

cs.CL cs.CY

Penulis (4)

Jan Batzner

Volker Stocker

Stefan Schmid

Gjergji Kasneci

Format Sitasi

APA MLA BibTeX

Batzner, J., Stocker, V., Schmid, S., Kasneci, G. (2025). Sycophancy Claims about Language Models: The Missing Human-in-the-Loop. https://arxiv.org/abs/2512.00656

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓