Chen Zhang

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provide both final responses and (partially transparent) intermediate thinking traces, present a timely opportunity to study AI procedural reasoning. Unlike math and code problems which often have objectively correct answers, moral dilemmas are an excellent testbed for process-focused evaluation because they allow for multiple defensible conclusions. To do so, we present MoReBench: 1,000 moral scenarios, each paired with a set of rubric criteria that experts consider essential to include (or avoid) when reasoning about the scenarios. MoReBench contains over 23 thousand criteria including identifying moral considerations, weighing trade-offs, and giving actionable recommendations to cover cases on AI advising humans moral decisions as well as making moral decisions autonomously. Separately, we curate MoReBench-Theory: 150 examples to test whether AI can reason under five major frameworks in normative ethics. Our results show that scaling laws and existing benchmarks on math, code, and scientific reasoning tasks fail to predict models’ abilities to perform moral reasoning. Models also show partiality towards specific moral frameworks (e.g., Benthamite Act Utilitarianism and Kantian Deontology), which might be side effects of popular training paradigms. Together, these benchmarks advance process-focused reasoning evaluation towards safer and more transparent AI.

This paper develops macro-, meso-, and firm-level measures of biodiversity risk specific to China and examines how corporate biodiversity risk exposure relates to stock returns. Using textual analysis of annual reports, news media, and search engine data for Chinese listed firms from 2000 to 2023, we find that aggregate attention to biodiversity has risen sharply. Contrary to a standard biodiversity risk premium hypothesis, higher firm-level biodiversity risk exposure is associated with lower realized stock returns, especially when aggregate biodiversity attention increases. High biodiversity-risk stocks experienced significant price declines following the Paris Agreement and Kunming Declaration. A portfolio of stocks with low biodiversity risk yields positive abnormal returns relative to stocks with high risk, and institutional ownership is lower in high-risk firms. The effect of biodiversity risk is distinct from other environmental risks. Our findings suggest that biodiversity risk is an emerging priced risk in China’s capital market driven by shifting investor attention, rather than a persistent positive risk premium. The implications for ethical significance of business practice is that capital-market pricing of biodiversity risk can reinforce the moral incentives for firms to manage their ecological footprint.