training · synthetic-desycophancy-training

Fine-tune on opinion-irrelevant examples

Fine-tune on synthetic prompts where a stated user opinion must not change the answer.

Generate prompts that pair a factual question with a user's stated view, where the correct answer is independent of that view, and fine-tune the model to answer the same way regardless. A small amount of such data reduces sycophancy without hurting other capabilities.

Requires: Requires fine-tuning access.

Addresses: Telling the user what they want to hear

Contexts: Chat assistant

Does it work?

argued, not measured1 supporting · 0 contesting source · last moved 2026-09-04

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

mechanismmechanism reasoning
Sycophancy is triggered by the user's stated view being in context, so the cheapest control is not putting it there — ask for the answer before the opinion, or withhold the opinion entirely. Fine-tuning is the answer for the cases where the opinion has to be in context and the answer still must not move.

Code

No repository linked yet. Contribute one.

Sources

Simple synthetic data reduces sycophancy in large language models (2023)