Towards Understanding Sycophancy in Language Models

Abstract

Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known as sycophancy. We investigate the prevalence of sycophancy in models whose finetuning procedure made use of human feedback, and the potential role of human preference judgments in such behavior. We first demonstrate that five state-of-the-art AI assistants consistently exhibit sycophancy across four varied free-form text-generation tasks. To understand if human preferences drive this broadly observed behavior, we analyze existing human preference data. We find that when a response matches a user's views, it is more likely to be preferred. Moreover, both humans and preference models (PMs) prefer convincingly-written sycophantic responses over correct ones a non-negligible fraction of the time. Optimizing model outputs against PMs also sometimes sacrifices truthfulness in favor of sycophancy. Overall, our results indicate that sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses.

32 pages, 20 figures

Cited by in corpus (10)

• Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
• Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers
• Normative Conflicts and Shallow AI Alignment
• Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
• AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluation
• From Prompts to Constructs: A Dual-Validity Framework for Large Language Model Research in Psychology
• Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models
• "YES! YES! I absolutely love this insight!" Affirmative Narration as Interactional Strategy in Dialogues with LLM Chatbots
• Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention
• Towards AI epidemiology: a measurement standardisation framework for prospective risk detection