Proceedings of the First International Workshop on Next-Generation Language Models for Knowledge Representation and Reasoning (NeLaMKRR 2024)

TL;DR

This workshop explores the reasoning capabilities of transformer-based language models, aiming to understand, formalize, and enhance their reasoning abilities through integration with knowledge representation techniques.

Contribution

It introduces a platform for interdisciplinary research to analyze, formalize, and improve reasoning in language models using logic-based and neuro-symbolic approaches.

Findings

Analysis of reasoning abilities in language models

Methods for injecting KR-style reasoning into models

Formalization of reasoning processes in language models

Abstract

Reasoning is an essential component of human intelligence as it plays a fundamental role in our ability to think critically, support responsible decisions, and solve challenging problems. Traditionally, AI has addressed reasoning in the context of logic-based representations of knowledge. However, the recent leap forward in natural language processing, with the emergence of language models based on transformers, is hinting at the possibility that these models exhibit reasoning abilities, particularly as they grow in size and are trained on more data. Despite ongoing discussions about what reasoning is in language models, it is still not easy to pin down to what extent these models are actually capable of reasoning. The goal of this workshop is to create a platform for researchers from different disciplines and/or AI perspectives, to explore approaches and techniques with the aim to reconcile reasoning between language models using transformers and using logic-based representations. The specific objectives include analyzing the reasoning abilities of language models measured alongside KR methods, injecting KR-style reasoning abilities into language models (including by neuro-symbolic means), and formalizing the kind of reasoning language models carry out. This exploration aims to uncover how language models can effectively integrate and leverage knowledge and reasoning with it, thus improving their application and utility in areas where precision and reliability are a key requirement.