Teaching Probabilistic Logical Reasoning to Transformers
This addresses the challenge of making language models more robust in uncertain reasoning tasks, which is incremental as it builds on existing fine-tuning methods.
The paper tackles the problem of transformer-based language models struggling with reasoning over uncertain text by proposing Probabilistic Constraint Training (PCT), a fine-tuning approach that improves their probabilistic logical reasoning and enables handling of novel situations like higher reasoning depth and new domains.
In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large Language Models (LLMs). Our evaluation results show that both generations of language models struggle with reasoning over uncertain text. We propose a novel end-to-end fine-tuning approach, Probabilistic Constraint Training (PCT), that utilizes probabilistic logical rules as constraints in the fine-tuning phase without relying on these rules in the inference stage. To assess the effectiveness of PCT, we utilize the related corpora and, additionally, create a new and more challenging benchmark that, unlike the previous ones, uses instance-specific rules. Our study demonstrates that PCT improves the transformer-based language model's intrinsic reasoning and makes their probabilistic logical reasoning process more explicit and explainable. Furthermore, PCT equips these models to effectively handle novel situations, including higher reasoning depth, new domains, and complex probabilistic structures.