The study, titled 'The pain axis: LLMs represent self-directed harm and act to relieve it', was published as a preprint on arXiv on September 12, 2026.

AI research advances and the benchmarks used to measure progress.

Large language models (LLMs) are advanced AI systems trained on massive text datasets to understand, generate, and reason about human language, powering applications such as chatbots, code generation, summarization, and scientific discovery.