Total: 1
Humans have strong capabilities of decomposition and composition in natural-to-formal language conversion (N2F) when faced with an unfamiliar formal language, and can easily cope with compositional gaps and counter-intuitive symbolic names. To investigate whether large language models (LLMs) have this set of basic capabilities in N2F, we propose the STD framework. This framework semi-automatically performs sample and task construction, allowing decoupled evaluation of the set of decomposition and composition capabilities of LLMs in N2F. Based on this framework, we evaluate and analyze the most advanced LLMs, and the main findings include that: (1) the LLMs are deficient in both decomposition and composition; (2) the LLMs show a wide coverage of error types that can be attributed to deficiencies in natural language understanding and the learning and use of symbolic systems; (3) compositional gaps and counter-intuitive symbolic names both affect the decomposition and composition of the LLMs. Our work provides a new perspective for investigating the basic capabilities of decomposition and composition of LLMs in N2F. The detailed analysis of deficiencies and attributions can help subsequent improvements of LLMs.