提升语言模型的符号翻译以增强逻辑推理
Improving Symbolic Translation of Language Models for Logical Reasoning
AI总结：
本文通过微调和增量推理框架，提升小型语言模型在逻辑推理中的符号翻译能力，减少错误率并提高推理性能。
摘要：
形式语言用于演绎逻辑推理与语言模型（LMs）相契合，将自然语言（NL）转换为一阶逻辑（FOL）并利用外部求解器可形成可验证且可靠的推理系统。然而，较小的LMs在这一翻译任务中常表现出困难，常因格式和翻译错误产生错误的符号输出。现有方法通常依赖自我迭代来纠正这些错误，但此类方法严重依赖底层模型的能力。为此，我们首先分类常见错误并使用大型语言模型合成的数据对较小的LMs进行微调。评估基于定义的错误类别进行。我们引入增量推理，将推理分为两个阶段，谓词生成和FOL翻译，从而更好地控制模型行为并提高谓词指标所衡量的生成质量。此分解框架也使能够使用验证模块，针对谓词 arity 错误进一步提升性能。我们的研究在四个逻辑推理数据集中评估了三种模型家族。全面的微调、增量推理和验证模块降低了错误率，提高了谓词覆盖率，并提高了较小LMs的推理性能，使我们更接近开发可靠且可访问的符号推理系统。
英文摘要：
The use of formal language for deductive logical reasoning aligns well with language models (LMs), where translating natural language (NL) into first-order logic (FOL) and employing an external solver results in a verifiable and therefore reliable reasoning system. However, smaller LMs often struggle with this translation task, frequently producing incorrect symbolic outputs due to formatting and translation errors. Existing approaches typically rely on self-iteration to correct these errors, but such methods depend heavily on the capabilities of the underlying model. To address this, we first categorize common errors and fine-tune smaller LMs using data synthesized by large language models. The evaluation is performed using the defined error categories. We introduce incremental inference, which divides inference into two stages, predicate generation and FOL translation, providing greater control over model behavior and enhancing generation quality as measured by predicate metrics. This decomposition framework also enables the use of a verification module that targets predicate-arity errors to further improve performance. Our study evaluates three families of models across four logical-reasoning datasets. The comprehensive fine-tuning, incremental inference, and verification modules reduce error rates, increase predicate coverage, and improve reasoning performance for smaller LMs, moving us closer to developing reliable and accessible symbolic-reasoning systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
