Probing Linguistic Information For Logical Inference In Pre-trained Language Models

2021/12/03 by Zeming Chen, Chen, Zeming, Qiyue Gao +1 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Deep linguistic processing #ENCODE #FOS: Computer and information sciences #Inference #Language model #Linguistic description #Linguistics #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Natural language #Natural language processing #Natural language understanding #Topic Modeling #cs.AI #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.2112.01753

published in arXiv (Cornell University) (Cornell University) · AAAI 2022 camera ready version

openalex publication_date 2021/12/03 · arxiv created 2022/03/21 · arxiv updated 2022/03/22 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28

Abstract

Progress in pre-trained language models has led to a surge of impressive results on downstream tasks for natural language understanding. Recent work on probing pre-trained language models uncovered a wide range of linguistic properties encoded in their contextualized representations. However, it is unclear whether they encode semantic knowledge that is crucial to symbolic inference methods. We propose a methodology for probing linguistic information for logical inference in pre-trained language model representations. Our probing datasets cover a list of linguistic phenomena required by major symbolic inference systems. We find that (i) pre-trained language models do encode several types of linguistic information for inference, but there are also some types of information that are weakly encoded, (ii) language models can effectively learn missing linguistic information through fine-tuning. Overall, our findings provide insights into which aspects of linguistic information for logical inference do language models and their pre-training procedures capture. Moreover, we have demonstrated language models' potential as semantic and background knowledge bases for supporting symbolic inference methods.

Cited by

• Rethinking Knowledge Distillation in Collaborative Machine Learning: Memory, Knowledge, and Their Interactions
• Linearly Decoding Refused Knowledge in Aligned Language Models
• An Efficient Private GPT Never Autoregressively Decodes

Related

• Are Pretrained Language Models Symbolic Reasoners Over Knowledge?
• Do Large Language Models Understand Logic or Just Mimick Context?
• APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
• Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?
• Probing Natural Language Inference Models through Semantic Fragments