用大模型指导符号模型，让分类更透明且准确
LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines
- 用大模型生成语义子意图，分三阶段合成数据扩充语义
- 符号模型提取高置信度语义线索，使逻辑与大模型语义对齐
- 无需运行大模型，仍达BERT水平，适合需要解释性的场景
预训练语言模型（如BERT）提供强大语义表征但成本高且不透明，而符号模型如Tsetlin机（TM）具有可解释性但缺乏语义泛化能力。本文提出一种语义自举框架，将大模型知识转化为符号形式，结合可解释性与语义能力。给定类别标签后，大模型生成子意图，通过三阶段课程（种子、核心、丰富）引导合成数据生成，扩展语义多样性。非否定型Tsetlin机（NTM）从这些样本中学习，提取高置信度文字作为可解释的语义线索。将这些线索注入真实数据，使TM能将逻辑条款与大模型推断的语义对齐。该方法无需嵌入或运行时调用大模型，却赋予符号模型预训练语义先验。在多个文本分类任务中，其可解释性和准确性优于基础TM，性能接近BERT，同时保持完全符号化和高效。
原文摘要 · Abstract (English)
Pretrained language models (PLMs) like BERT provide strong semantic representations but are costly and opaque, while symbolic models such as the Tsetlin Machine (TM) offer transparency but lack semantic generalization. We propose a semantic bootstrapping framework that transfers LLM knowledge into symbolic form, combining interpretability with semantic capacity. Given a class label, an LLM generates sub-intents that guide synthetic data creation through a three-stage curriculum (seed, core, enriched), expanding semantic diversity. A Non-Negated TM (NTM) learns from these examples to extract high-confidence literals as interpretable semantic cues. Injecting these cues into real data enables a TM to align clause logic with LLM-inferred semantics. Our method requires no embeddings or runtime LLM calls, yet equips symbolic models with pretrained semantic priors. Across multiple text classification tasks, it improves interpretability and accuracy over vanilla TM, achieving performance comparable to BERT while remaining fully symbolic and efficient.
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。