Exploring the effects of human-centered AI explanations on trust and reliance
Transparency is widely regarded as crucial for the responsible real-world deployment of artificial intelligence (AI) and is considered an essential prerequisite to establishing trust in AI. There are several approaches to enabling transparency, with one promising attempt being human-centered explana...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Computer Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcomp.2023.1151150/full |
| _version_ | 1797778317816889344 |
|---|---|
| author | Nicolas Scharowski Sebastian A. C. Perrig Melanie Svab Klaus Opwis Florian Brühlmann |
| author_facet | Nicolas Scharowski Sebastian A. C. Perrig Melanie Svab Klaus Opwis Florian Brühlmann |
| author_sort | Nicolas Scharowski |
| collection | DOAJ |
| description | Transparency is widely regarded as crucial for the responsible real-world deployment of artificial intelligence (AI) and is considered an essential prerequisite to establishing trust in AI. There are several approaches to enabling transparency, with one promising attempt being human-centered explanations. However, there is little research into the effectiveness of human-centered explanations on end-users' trust. What complicates the comparison of existing empirical work is that trust is measured in different ways. Some researchers measure subjective trust using questionnaires, while others measure objective trust-related behavior such as reliance. To bridge these gaps, we investigated the effects of two promising human-centered post-hoc explanations, feature importance and counterfactuals, on trust and reliance. We compared these two explanations with a control condition in a decision-making experiment (N = 380). Results showed that human-centered explanations can significantly increase reliance but the type of decision-making (increasing a price vs. decreasing a price) had an even greater influence. This challenges the presumed importance of transparency over other factors in human decision-making involving AI, such as potential heuristics and biases. We conclude that trust does not necessarily equate to reliance and emphasize the importance of appropriate, validated, and agreed-upon metrics to design and evaluate human-centered AI. |
| first_indexed | 2024-03-12T23:15:30Z |
| format | Article |
| id | doaj.art-80f8202d94494633afb0fb84b85f8d58 |
| institution | Directory Open Access Journal |
| issn | 2624-9898 |
| language | English |
| last_indexed | 2024-03-12T23:15:30Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computer Science |
| spelling | doaj.art-80f8202d94494633afb0fb84b85f8d582023-07-17T08:26:50ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982023-07-01510.3389/fcomp.2023.11511501151150Exploring the effects of human-centered AI explanations on trust and relianceNicolas ScharowskiSebastian A. C. PerrigMelanie SvabKlaus OpwisFlorian BrühlmannTransparency is widely regarded as crucial for the responsible real-world deployment of artificial intelligence (AI) and is considered an essential prerequisite to establishing trust in AI. There are several approaches to enabling transparency, with one promising attempt being human-centered explanations. However, there is little research into the effectiveness of human-centered explanations on end-users' trust. What complicates the comparison of existing empirical work is that trust is measured in different ways. Some researchers measure subjective trust using questionnaires, while others measure objective trust-related behavior such as reliance. To bridge these gaps, we investigated the effects of two promising human-centered post-hoc explanations, feature importance and counterfactuals, on trust and reliance. We compared these two explanations with a control condition in a decision-making experiment (N = 380). Results showed that human-centered explanations can significantly increase reliance but the type of decision-making (increasing a price vs. decreasing a price) had an even greater influence. This challenges the presumed importance of transparency over other factors in human decision-making involving AI, such as potential heuristics and biases. We conclude that trust does not necessarily equate to reliance and emphasize the importance of appropriate, validated, and agreed-upon metrics to design and evaluate human-centered AI.https://www.frontiersin.org/articles/10.3389/fcomp.2023.1151150/fullAIXAIHCXAItrustreliancetransparency |
| spellingShingle | Nicolas Scharowski Sebastian A. C. Perrig Melanie Svab Klaus Opwis Florian Brühlmann Exploring the effects of human-centered AI explanations on trust and reliance Frontiers in Computer Science AI XAI HCXAI trust reliance transparency |
| title | Exploring the effects of human-centered AI explanations on trust and reliance |
| title_full | Exploring the effects of human-centered AI explanations on trust and reliance |
| title_fullStr | Exploring the effects of human-centered AI explanations on trust and reliance |
| title_full_unstemmed | Exploring the effects of human-centered AI explanations on trust and reliance |
| title_short | Exploring the effects of human-centered AI explanations on trust and reliance |
| title_sort | exploring the effects of human centered ai explanations on trust and reliance |
| topic | AI XAI HCXAI trust reliance transparency |
| url | https://www.frontiersin.org/articles/10.3389/fcomp.2023.1151150/full |
| work_keys_str_mv | AT nicolasscharowski exploringtheeffectsofhumancenteredaiexplanationsontrustandreliance AT sebastianacperrig exploringtheeffectsofhumancenteredaiexplanationsontrustandreliance AT melaniesvab exploringtheeffectsofhumancenteredaiexplanationsontrustandreliance AT klausopwis exploringtheeffectsofhumancenteredaiexplanationsontrustandreliance AT florianbruhlmann exploringtheeffectsofhumancenteredaiexplanationsontrustandreliance |