Teaching Probabilistic Logical Reasoning to Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nafar, Aliakbar, Venable, Kristen Brent, Kordjamshidi, Parisa
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914672391749632
author Nafar, Aliakbar
Venable, Kristen Brent
Kordjamshidi, Parisa
author_facet Nafar, Aliakbar
Venable, Kristen Brent
Kordjamshidi, Parisa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2305_13179
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Teaching Probabilistic Logical Reasoning to Transformers
Nafar, Aliakbar
Venable, Kristen Brent
Kordjamshidi, Parisa
Computation and Language
Artificial Intelligence
I.2.7
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.
title Teaching Probabilistic Logical Reasoning to Transformers
topic Computation and Language
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2305.13179