Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice

Journal article

Large language models (LLMs) play a vital role in almost every domain in today\u27s organizations. In the context of this work, we highlight the use of LLMs for sentiment analysis (SA) and explainability. Specifically, we contribute a novel technique to leverage LLMs as a post-hoc model-independent tool for the explainability of SA. We applied our technique in the financial domain for currency-pair price predictions using open news feed data merged with market prices. Our application shows that the developed technique is not only a viable alternative to using conventional eXplainable AI but can also be fed back to enrich the input to the machine learning (ML) model to better predict future currency-pair values. We envision our results could be generalized to employing explainability as a conventional enrichment for ML input for better ML predictions in general.7 pages, 3 figures, AIFin@ECAI 202

Authors: Watson, DS; Gultchin, L; Taly, A; Floridi, L

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Journal: Minds and Machines
• Volume: 32
• Issue: 1
• Pages: 185-218
• Publication date: 2022-03-16
• DOI: 10.1007/s11023-022-09598-7
• EISSN: 1572-8641
• ISSN: 0924-6495
• Language: English
• Keywords: Watson; Management science; Set (abstract data type); Causality (physics); Philosophy of science; Epistemology; Algorithm; Economics; Artificial intelligence; Context (archaeology); Computer science; Theory of computation