Context Is King: Large Language Models’ Interpretability in Divergent Knowledge Scenarios
Open Access
- 24 January 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (3) , 1192
Abstract
Large language models (LLMs) have revolutionized the field of artificial intelligence in both academia and industry, transforming how we communicate, search for information, and create content. However, these models face knowledge cutoffs and costly updates, driving a new ecosystem for LLM-based applications that leverage interaction techniques to extend capabilities and facilitate knowledge updates. As these models grow more complex, understanding their internal workings becomes increasingly challenging, posing significant issues for transparency, interpretability, and explainability. This paper proposes a novel approach to interpretability by shifting the focus to understanding the model’s functionality within specific contexts through interaction techniques. Rather than dissecting the LLM itself, we explore how contextual information and interaction techniques can elucidate the model’s thought processes. To this end, we introduce the Context-Driven Divergent Knowledge Evaluation (CDK-E) methodology, along with the Divergent Knowledge Dataset (DKD), for evaluating the interpretability of LLMs in context-specific scenarios that diverge from the model’s inherent knowledge. The empirical results demonstrate that advanced LLMs achieve high alignment with divergent contexts, validating our hypothesis that contextual information significantly enhances interpretability. Moreover, the strong correlation between LLM-based metrics and semantic metrics confirms the reliability of our evaluation framework.Keywords
Funding Information
- Galician Innovation Agency (GAIN) (ED431B 2024/36)
- Xunta de Galicia (ED431B 2024/36)
- European Union (ED431B 2024/36)
This publication has 33 references indexed in Scilit:
- Explainability for Large Language Models: A SurveyACM Transactions on Intelligent Systems and Technology, 2024
- Benchmarking Large Language Models for News SummarizationTransactions of the Association for Computational Linguistics, 2024
- In-Context Retrieval-Augmented Language ModelsTransactions of the Association for Computational Linguistics, 2023
- Algorithms to estimate Shapley value feature attributionsNature Machine Intelligence, 2023
- Attention is not all you need: the complicated case of ethically using large language models in healthcare and medicineEBioMedicine, 2023
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language ProcessingACM Computing Surveys, 2023
- A novel method using explainable artificial intelligence (XAI)-based Shapley Additive Explanations for spatial landslide prediction using Time-Series SAR datasetGondwana Research, 2022
- Large language models associate Muslims with violenceNature Machine Intelligence, 2021
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020
- Techniques for interpretable machine learningCommunications of the ACM, 2019