用编码器架构一次前向传播完成可解释的自然语言推理
Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass
- 基于纯编码器结构，一次性提取原子事实并完成推理
- 在分布内准确率相当，分布外和对抗场景下鲁棒性显著提升
- 仅需合成推理链训练，无需生成式模型，适合实际部署
自然语言推理（NLI）及相关任务（如自动查证）近年来采用原子事实分解以提升可解释性和鲁棒性。现有方法依赖资源密集型生成式大模型进行分解。本文提出JEDI，一种仅使用编码器的架构，可在不依赖生成模型的情况下，联合完成提取式原子事实分解与可解释推理。为支持训练，我们构建了一个覆盖多个NLI基准的大型合成推理链语料库。实验表明，JEDI在分布内达到具有竞争力的准确率，且在分布外和对抗设置下显著优于仅依赖提取式推理监督的模型。结果表明，利用纯编码器架构与合成推理链，即可实现NLI中的可解释性与鲁棒泛化。代码与数据见https://jedi.nicpopovic.com。
原文摘要 · Abstract (English)
Recent works in Natural Language Inference (NLI) and related tasks, such as automated fact-checking, employ atomic fact decomposition to enhance interpretability and robustness. For this, existing methods rely on resource-intensive generative large language models (LLMs) to perform decomposition. We propose JEDI, an encoder-only architecture that jointly performs extractive atomic fact decomposition and interpretable inference without requiring generative models during inference. To facilitate training, we produce a large corpus of synthetic rationales covering multiple NLI benchmarks. Experimental results demonstrate that JEDI achieves competitive accuracy in distribution and significantly improves robustness out of distribution and in adversarial settings over models based solely on extractive rationale supervision. Our findings show that interpretability and robust generalization in NLI can be realized using encoder-only architectures and synthetic rationales. Code and data available at https://jedi.nicpopovic.com
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。