Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

arXiv:2304.01665v3 Announce Type: replace
Abstract: Language models' (LMs) proficiency in handling deterministic symbolic reasoning and rule-based tasks remains limited due to their dependency implicit learning on textual data. To endow LMs with genuine rule comprehension abilities, we propose "Neural Comprehension" - a framework that synergistically integrates compiled neural networks (CoNNs) into the standard transformer architecture. CoNNs are neural modules designed to explicitly encode rules through artificially generated attention weights. By incorporating CoNN modules, the Neural Comprehension framework enables LMs to …

abstract arxiv cs.cl data framework language language models lms networks neural networks operations reasoning symbolic reasoning tasks textual type