Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models

arXiv:2401.11725v2 Announce Type: replace
Abstract: Symbols (or more broadly, non-natural language textual representations) such as numerical sequences, molecular formulas, and table delimiters widely exist, playing important roles in various tasks such as abstract reasoning, chemical property prediction, and table question answering. Despite the impressive natural language comprehension capabilities of large language models (LLMs), their reasoning abilities for symbols remain inadequate, which could attributed to the difference between symbol representations and general natural languages. We propose symbol-to-language (S2L), a tuning-free method …

arxiv conversion cs.cl language language models speak type