jablonkagroup/corral-reasoning-annotations
收藏资源简介:
该数据集是Corral集合的一部分,伴随论文《AI科学家在不进行科学推理的情况下产生结果》。它包含带有LLM生成的认识论标注的标注评估轨迹,覆盖Corral基准测试。数据集以单一配置形式提供,每一行对应一个待标注文件,表示为一个标注的轨迹实例。这些标注是由LLM标注器生成的,标注器识别出这些案例中智能体没有进行科学推理。该资源旨在用于审计、定性分析和科学智能体行为的过程级研究,而不是用于通用模型预训练。
This dataset is part of the Corral collection accompanying the paper AI scientists produce results without reasoning scientifically. It contains annotated evaluation traces with LLM-generated epistemic annotations across the Corral benchmark. The dataset is exposed as a single configuration, where each row corresponds to one file to annotate, represented as an annotated trace instance. The included annotations were produced by an LLM annotator that identified these cases as ones where the agents do not reason scientifically. This resource is intended for auditing, qualitative analysis, and process-level study of scientific-agent behaviour rather than for general-purpose model pre-training.




