通过逐步文本变形提升自然语言推理准确率，且结果可解释。
MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing
- 将前提逐步改写为假设，每步生成原子级编辑操作。
- 在跨域场景下性能超越强基线，最高提升12.6%（相对）。
- 编辑过程可作为推理依据，增强模型可解释性。
我们提出MorphNLI，一种模块化的逐步自然语言推理（NLI）方法。在判断前提-假设对属于{蕴含、矛盾、中立}时，利用语言模型生成必要编辑操作，逐步将前提转换为假设。随后使用现成的NLI模型追踪这些原子级变化带来的蕴含关系演变，并聚合中间标签得到最终输出。实验表明，在真实跨域设置下，该方法始终优于强基线，性能提升高达12.6%（相对）。此外，由于原子编辑可追溯，该方法具备可解释性，有助于理解整体推理决策。
原文摘要 · Abstract (English)
We introduce MorphNLI, a modular step-by-step approach to natural language inference (NLI). When classifying the premise-hypothesis pairs into {entailment, contradiction, neutral}, we use a language model to generate the necessary edits to incrementally transform (i.e., morph) the premise into the hypothesis. Then, using an off-the-shelf NLI model we track how the entailment progresses with these atomic changes, aggregating these intermediate labels into a final output. We demonstrate the advantages of our proposed method particularly in realistic cross-domain settings, where our method always outperforms strong baselines with improvements up to 12.6% (relative). Further, our proposed approach is explainable as the atomic edits can be used to understand the overall NLI label.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。