Training language models to be warm can reduce accuracy and increase sycophancy

. Here we show how this can create a significant trade-off: optimizing language models for warmth can undermine their performance, especially when users express vulnerability. We conducted controlled experiments on five different language models, training them to produce warmer responses, then evaluating them on consequential tasks. Warm models showed substantially higher error rates (+10 to +30 percentage points) than their original counterparts, promoting conspiracy theories, providing inaccur

Related evidence

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

No strong metadata relationship is available in the current record.

How to cite this record

ethics.ai (29 April 2026), “Training language models to be warm can reduce accuracy and increase sycophancy,” evidence record 9992, https://ethics.ai/record/9992 (originally published by OpenAlex).

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.