Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversion
This work addresses the problem of robust natural-to-formal language conversion for AI researchers, but it is incremental as it focuses on evaluating existing LLMs rather than proposing a new method.
The paper investigates whether large language models (LLMs) have strong decomposition and composition capabilities for natural-to-formal language conversion, finding that LLMs are deficient in both, with errors attributed to natural language understanding and symbolic system issues.
To achieve generalized and robust natural-to-formal language conversion (N2F), large language models (LLMs) need to have strong capabilities of decomposition and composition in N2F when faced with an unfamiliar formal language and be able to cope with compositional gaps and counter-intuitive symbolic names. To investigate whether LLMs have this set of basic capabilities in N2F, we propose the DEDC 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.