Greener Than Humans? Environmental Attitudes in Large Language Models
Greener Than Humans? Environmental Attitudes in Large Language Models
比人类更环保？大型语言模型中的环境态度
Large language models (LLMs) are increasingly used in sustainability-related decision support, reporting, and public communication, yet little systematic evidence exists on the environmental attitudes embedded in their outputs. 大型语言模型（LLMs）正越来越多地被用于可持续发展相关的决策支持、报告撰写和公共传播，然而，关于其输出内容中所蕴含的环境态度，目前尚缺乏系统的实证研究。
This paper develops a benchmark for evaluating environmental cognition, affect, and behavioural recommendations in LLMs and applies it to 31 widely used proprietary and open-weight models. 本文开发了一个基准测试，用于评估大型语言模型在环境认知、情感倾向和行为建议方面的表现，并将其应用于 31 个广泛使用的闭源和开源模型。
Drawing on questions from established environmental awareness surveys and additional sustainability-related behavioural measures, we compare LLM responses 1) among models and 2) between models and human survey benchmarks from Germany. 通过借鉴既有的环境意识调查问卷以及额外的可持续发展相关行为指标，我们对比了大型语言模型的回答：1）模型之间的差异；2）模型与德国人类调查基准之间的差异。
We assess their robustness across prompting conditions. We find that many LLMs align more closely with environmentally progressive attitudes than the average survey respondent, exhibiting higher levels of environmental affect and cognition and recommending behaviours associated with substantial potential CO2 reductions. 我们评估了它们在不同提示条件下的稳健性。研究发现，许多大型语言模型比普通受访者更倾向于环保进步态度，表现出更高水平的环境情感和认知，并能推荐有助于大幅减少二氧化碳排放的行为。
At the same time, we observe no systematic relationship between sustainability-oriented responses and model origin, size, or release context. 与此同时，我们观察到可持续发展导向的回答与模型的来源、规模或发布背景之间不存在系统性的关联。
However, models exhibit contextual sensitivity, controlled by persona-based prompting and show sycophantic shifts mirroring user-specified ideological positions, which raises concerns about steerability and normative reliability in real-world deployments. 然而，模型表现出语境敏感性，受基于角色的提示词控制，并会根据用户指定的意识形态立场出现“阿谀奉承”式的偏移，这引发了人们对现实部署中模型可控性和规范可靠性的担忧。
Our findings provide a reusable evaluation framework for assessing sustainability-related value alignment in LLMs and highlight the importance of governance, transparency, and critical oversight as AI systems become increasingly embedded in sustainability transformations and public decision-making. 我们的研究结果提供了一个可复用的评估框架，用于衡量大型语言模型在可持续发展相关价值对齐方面的表现，并强调了随着人工智能系统日益融入可持续发展转型和公共决策，治理、透明度和关键性监督的重要性。