Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversion

2025-01-24

AI Summary

This work addresses the limited decomposition and composition capabilities of large language models (LLMs) in natural language-to-formal language translation. To this end, we propose DEDC—the first evaluation framework enabling *disentangled* assessment of these two core reasoning abilities. DEDC employs semi-automated prompt engineering and structured task design to generate diagnostic samples, and integrates error attribution analysis with controlled-variable experiments to independently quantify decomposition (information splitting) and composition (symbolic recombination). Our empirical study reveals systematic deficiencies in both capabilities across mainstream LLMs; root causes include shallow natural language understanding and inadequate acquisition of formal symbol systems. Critically, a “composition gap”—the difficulty in correctly reassembling decomposed elements—and counterintuitive symbolic naming conventions significantly hinder performance. These findings establish a novel paradigm for rigorously evaluating and improving LLMs’ formal reasoning capabilities.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

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.

Problem

• Large Language Models
• Information Restructuring
• Unseen Token Handling

Innovation

• DEDC Framework
• Language Model Evaluation
• Symbol Handling Limitations