Towards Explainable and Language-Agnostic LLMs: Symbolic Reverse Engineering of Language at Scale
Large language models (LLMs) have achieved a milestone that undenia-bly changed many held beliefs in artificial intelligence (AI). However, there remains many limitations of these LLMs when it comes to true language understanding, limitations that are a byproduct of the under-lying architecture of deep neural networks. Moreover, and due to their subsymbolic nature, whatever knowledge these models acquire about how language works will always be buried in billions of microfeatures (weights), none of which is meaningful on its own, making such models hopelessly unexplainable. To address these limitations, we suggest com-bining the strength of symbolic representations with what we believe to be the key to the success of LLMs, namely a successful bottom-up re-verse engineering of language at scale. As such we argue for a bottom-up reverse engineering of language in a symbolic setting. Hints on what this project amounts to have been suggested by several authors, and we discuss in some detail here how this project could be accomplished.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reinterpreting 'the Company a Word Keeps': Towards Explainable and Ontologically Grounded Language Models
We argue that the relative success of large language models (LLMs) is not a reflection on the symbolic vs. subsymbolic debate but a reflection on employing a successful bottom-up strategy of a reverse engineering of lang…
Stochastic LLMs do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMs
In our opinion the exuberance surrounding the relative success of data-driven large language models (LLMs) is slightly misguided and for several reasons (i) LLMs cannot be relied upon for factual information since for LL…
Symbolic and Language Agnostic Large Language Models
We argue that the relative success of large language models (LLMs) is not a reflection on the symbolic vs. subsymbolic debate but a reflection on employing an appropriate strategy of bottom-up reverse engineering of lang…
Uncertainty Reasoning with Large Language Models for Explainable Disease Diagnosis
Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LLMs) excel at extracting latent information from natural language, th…
Medical DiagnosisFormal LogicTRACE-CS: A Synergistic Approach to Explainable Course Scheduling Using LLMs and Logic
We present TRACE-cs, a novel hybrid system that combines symbolic reasoning with large language models (LLMs) to address contrastive queries in scheduling problems. TRACE-cs leverages SAT solving techniques to encode sch…
Scheduling