Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Beyond the greenwash: do LLMs' ecologically sound decisions hold up under pressure?
Trent R. Northen, Mingxun Wang
Humans are increasingly using large language models (LLMs) in decision making processes throughout society. Unfortunately, models have biases, and these can be very difficult to me…
cs.CL2026
Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety
Trent R Northen, Mingxun Wang
Large language models (LLMs) trained on internet-scale corpora can exhibit systematic biases that increase the probability of unwanted behavior. In this study, we examined potentia…