We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is "trained" through collaborative interactions among multiple LLM agents rather than traditional backpropagation. The LLM agents produce rule-based Python code for a generator for the given domain, based on RDF triples only, with no in-domain human reference texts. The resulting system is fully interpretable, requires no supervised training data, and generates text nearly instantaneously using only a single CPU. Our experiments on the WebNLG and OpenDialKG data show that outputs produced by our approach reduce hallucination, with only slight fluency penalties compared to finetuned or prompted language models

翻译：我们提出了一种新颖的神经符号框架用于 RDF 到文本生成，其中模型通过多个 LLM 代理之间的协作交互而非传统的反向传播进行“训练”。LLM 代理仅基于 RDF 三元组（无需领域内人工参考文本）为给定领域生成基于规则的 Python 代码生成器。所得系统完全可解释，无需监督训练数据，且仅使用单个 CPU 即可近乎即时地生成文本。我们在 WebNLG 和 OpenDialKG 数据上的实验表明，该方法产生的输出减少了幻觉现象，与微调或提示的语言模型相比仅存在轻微的流畅性损失。