From f55d68ce3dd055646b1db36e4e45bd851e8c5603 Mon Sep 17 00:00:00 2001 From: Lilja77 Date: Thu, 16 Nov 2023 09:04:37 +0100 Subject: [PATCH] Update index.md --- content/pages/events/seminars/2023-09-27/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/pages/events/seminars/2023-09-27/index.md b/content/pages/events/seminars/2023-09-27/index.md index b34193a01..583419edc 100644 --- a/content/pages/events/seminars/2023-09-27/index.md +++ b/content/pages/events/seminars/2023-09-27/index.md @@ -8,5 +8,5 @@ venue: "Gothenburg and online" slides: "Alexander Berman 27.9.2023.pdf" --- -Abstract +Abstract: Recently, there has been a large interest in large language models (LLMs) such as GPT and their ability to engage in human-like dialogue and use commonsense reasoning. We experimentally investigate a specific aspect of these abilities, namely counterfactual explanations. The capacity to reason counterfactually and provide relevant explanations is particularly important when using AI to assist high-stake decisions and assessments such as credit approval or medical diagnostics. For example, if a loan applicant is denied credit, a counterfactual explanation conveys the conditions under which the credit would have been granted. By injecting a decision-making algorithm into the model's prompt and systematically probing and annotating responses for carefully chosen inputs, we study potential patterns in GPT's selection of counterfactual examples. Preliminary results indicate that when GPT 3.5 provides counterfactual explanations, it does not consider causal relations between variables in a way that one would expect from a model with strong commonsense reasoning capabilities. We discuss potential implications of these results for real-world applications and future research.