发表机构
School of Computing and Information Technology, University of Wollongong; School of Business, University of Wollongong; Business School, University of Sydney; Business School, Macquarie University（卧龙岗大学计算与信息技术学院; 卧龙岗大学商学院; 悉尼大学商学院; 麦考瑞大学商学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究将气候披露分类视为跨源适应问题，在11个大语言模型上研究定义、示例和微调三种策略，发现最强源内策略非最强跨源策略，随机示例跨源优势更可靠，定义转移最一致，源变化时简单策略更安全。
AI 中文摘要
气候披露分类是分析企业气候披露的一项基础任务，但此类披露出现在许多不同来源中，如年报、新闻稿和财报电话会议，它们在长度、目的和写作风格上存在差异。现有评估大多在单一来源内进行，尚不清楚通用的大语言模型适应策略在源转移下是否仍有效。我们将气候披露分类重新定义为跨源适应问题，并使用两个具有相同标签空间但来自不同来源的语料库，研究了三种广泛使用的适应策略——定义、示例和微调——在11个开源和闭源大语言模型上的效果。我们发现，所有策略平均都带来了积极的跨源收益，但最强的源内策略并非最强的跨源策略：基于相似度的检索和LoRA微调在源内收益最大，但在源转移下优势丧失最多；随机选择的少样本示例，作为较弱的源内基线，更可靠地保留了其优势；定义转移最一致，不过只有当它们的粒度与目标文本匹配时才成立。在这些策略中，当源发生变化时，越简单往往越安全。
英文摘要
Climate disclosure classification is a fundamental task for analysing corporate climate disclosures, yet such disclosures appear in many different sources -- annual reports, press releases, and earnings calls -- that differ in length, purpose, and writing style. Existing evaluations are mostly conducted within a single source, leaving open whether common LLM adaptation strategies remain effective under source shift. We reframe climate disclosure classification as a cross-source adaptation problem and study three widely used adaptation strategies -- definitions, examples, and fine-tuning -- across eleven open- and closed-source LLMs, using two corpora that share the same label space but come from different sources. We find that all strategies bring positive cross-source gains on average, but the strongest in-source strategies are not the strongest cross-source ones: similarity-based retrieval and LoRA fine-tuning gain most in-source but lose most of that advantage under source shift; randomly selected few-shot examples, a weaker in-source baseline, retain their advantage more reliably; definitions transfer most consistently, though only when their granularity matches the target text. Across these strategies, when the source changes, simpler is often safer.
CommentsAccepted to Findings of EMNLP 2026. Camera-ready version
