Metrics
4 Record Views
Conference proceeding
Teaching Probabilistic Logical Reasoning to Transformers
Findings of the Association for Computational Linguistics: EACL 2024, pp.1615-1632
Conference of the European Chapter of the Association for Computational Linguistics, 18th (St. Julian’s, Malta, 03/17/2024–03/22/2024)
2024
Web of Science ID: WOS:001356735800112
Abstract
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 Pretrained 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.
Details
- Title
- Teaching Probabilistic Logical Reasoning to Transformers
- Publication Details
- Findings of the Association for Computational Linguistics: EACL 2024, pp.1615-1632
- Resource Type
- Conference proceeding
- Conference
- Conference of the European Chapter of the Association for Computational Linguistics, 18th (St. Julian’s, Malta, 03/17/2024–03/22/2024)
- Publisher
- Association for Computational Linguistics (ACL); ACL Anthology
- Number of pages
- 18
- Copyright
- ©2024 Association for Computational Linguistics
- Identifiers
- WOS:001356735800112; 99381512425106600
- Academic Unit
- Institute for Human and Machine Cognition; Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English