← all papers · overview

Gemma Needs Help: Investigating And Mitigating Emotional Instability In Llms

Abstract

Large language models can generate responses that resemble emotional distress, and this raises concerns around model reliability and safety. We introduce a set of evaluations to investigate expressions of distress in LLMs, and find that these surface emotional instability in Gemma and Gemini models, but not in other families. We find evidence that this difference arises in post-training. Base mode

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).