arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.09207cs.AIcs.CL
收藏

P-FOLIO:通过丰富的人工编写推理链评估和改进逻辑推理

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains

Yale University(耶鲁大学);Harvard University(哈佛大学);NVIDIA(英伟达公司);Salesforce Research(Salesforce研究院)
Simeng Han, Aaron Yu, Rui Shen, Zhenting Qi, Martin Riddell, Wenfei Zhou, Yujie Qiao, Yilun Zhao, Semih Yavuz, Ye Liu, Shafiq Joty, Yingbo Zhou, Caiming Xiong, … 展开作者

Simeng Han, Aaron Yu, Rui Shen, Zhenting Qi, Martin Riddell, Wenfei Zhou, Yujie Qiao, Yilun Zhao, Semih Yavuz, Ye Liu, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Dragomir Radev, Rex Ying, Arman Cohan

AI总结:

提出P-FOLIO人工标注数据集,通过单步推理规则分类评估并利用多样本提示与微调显著提升LLM逻辑推理能力,在域外数据集上性能提升超10%。

摘要:

现有的理解LLM逻辑推理能力的方法依赖于二元蕴含分类或合成的理由,这不足以充分调查模型的能力。我们提出了P-FOLIO,一个由人类标注的数据集,包含针对一组同样由人类编写的现实逻辑推理故事的多样且复杂的推理链。P-FOLIO通过一种标注协议收集,该协议促使人类以逐步方式为一阶逻辑推理问题标注结构良好的自然语言证明。P-FOLIO中的推理步骤数量从0到20不等。我们进一步使用P-FOLIO来评估和改进大型语言模型(LLM)的推理能力。我们通过单步推理规则分类以细粒度评估LLM推理能力,其推理规则比以往工作更加多样且复杂程度更高。鉴于单个模型生成的推理链可能采取与人工标注完全不同的路径,我们从模型中采样多个推理链,并使用pass@k指标评估模型生成推理链的质量。我们表明,通过多次提示和微调,人工编写的推理链显著提升了LLM的逻辑推理能力。此外,在P-FOLIO上微调Llama3-7B使模型在其他三个域外逻辑推理数据集上的性能提升了10%或更多。我们还进行了详细分析,以展示最强大的LLM在推理方面的不足之处。我们将公开发布数据集和代码。

英文摘要:

Existing methods on understanding the capabilities of LLMs in logical reasoning rely on binary entailment classification or synthetically derived rationales, which are not sufficient for proper investigation of model's capabilities. We present P-FOLIO, a human-annotated dataset consisting of diverse and complex reasoning chains for a set of realistic logical reasoning stories also written by humans. P-FOLIO is collected with an annotation protocol that facilitates humans to annotate well-structured natural language proofs for first-order logic reasoning problems in a step-by-step manner. The number of reasoning steps in P-FOLIO span from 0 to 20. We further use P-FOLIO to evaluate and improve large-language-model (LLM) reasoning capabilities. We evaluate LLM reasoning capabilities at a fine granularity via single-step inference rule classification, with more diverse inference rules of more diverse and higher levels of complexities than previous works. Given that a single model-generated reasoning chain could take a completely different path than the human-annotated one, we sample multiple reasoning chains from a model and use pass@k metrics for evaluating the quality of model-generated reasoning chains. We show that human-written reasoning chains significantly boost the logical reasoning capabilities of LLMs via many-shot prompting and fine-tuning. Furthermore, fine-tuning Llama3-7B on P-FOLIO improves the model performance by 10% or more on three other out-of-domain logical reasoning datasets. We also conduct detailed analysis to show where most powerful LLMs fall short in reasoning. We will release the dataset and code publicly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑