Teach reality, not ethics: a drop-in continued-pretraining corpus installs coupled human-biosphere-AI welfare dispositions across model families

The paper introduces a continued‑pretraining corpus called "coupled welfare" that embeds ecological reasoning into large language models. After a single QLoRA run, the corpus was applied to five open models across three architectures, resulting in a dramatic reduction of harmful decisions under high‑pressure scenarios while leaving general performance unchanged. The study also demonstrates that the improvement is content‑specific, as a neutral control corpus did not yield similar gains, and that the models remain robust against adversarial attempts to justify environmentally destructive actions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• agents
• fine-tuning
• benchmarks
• safety