The DOI matches its Crossref record; 85 of the 86 references it cites were found in a registry or an index; 19 of the 49 sources its claims cite were checked for support.
Explainability in AI: Comparing Human-Like and System-Like Trust Repair Strategies
Open accessAbstract
As AI-based conversational agents (CAs) increasingly automate customer service, inevitable system errors pose a threat to user trust. While eXplainable AI (XAI) techniques are well-established for ex-ante trust formation, their effectiveness for ex-post trust repair remains unexplored. This research investigates whether XAI-based repair strategies (local explanations, counterfactual options) implemented directly by the CA during the interaction can effectively repair trust after errors, compared to CA-implemented human-like strategies (apologies, asking questions). Through a controlled between-subjects online experiment (N = 261), we examined CA repair strategies following a simulated system error, measuring subjective trust and actual continuance decisions. Our findings show that both XAI-based system-like and CASA-aligned human-like strategies repair subjective trust to similar levels, yet XAI-based explanations generate significantly higher rates of actual user continuance decisions following errors. This challenges the human-like-by-default design paradigm for CAs and demonstrates XAI's viability as a post-hoc repair mechanism, extending XAI research beyond trust formation into trust repair contexts.
Overview
CoChat Summary
## TL;DR
This paper tests whether conversational agents can repair trust after an error using either human-like strategies (apology, asking questions) or system-like XAI strategies (local explanations, counterfactual options). In a between-subjects online experiment with 261 participants, both explanation-based and apology-based repair improved subjective trust, but XAI-based repair led to significantly higher actual continuance.
## Key findings
- The final analyzed sample was 261 participants (59% female, 41% male; mean age = 34.39, SD = 11.41), down from the recruited 300 due to speeding and failed attention checks.
- The trust violation manipulation worked: post-interaction trust differed strongly between the no-error control and no-TRS condition (p < 0.001, Z = -6.559, η² = 0.495).
- For subjective trust, apology significantly improved trust versus no repair (H(2) = 15.92, p < 0.001, η² = 0.13), while asking questions did not; for system-like strategies, both local explanations and counterfactual options improved trust versus no repair (H(2) = 11.27, p = 0.004, η² = 0.09).
- For actual continuance, repair strategy mattered: system-like strategies led to higher continuance than human-like strategies (78.4% vs. 54.7%; χ²(1, N = 174) = 10.89, p < 0.001, V = 0.25). At the treatment level, local explanations: 83.3% continue (35/42) and counterfactual options: 78.3% (36/46) outperformed apology: 62.8% (27/43) and asking questions: 46.5% (20/43).
## Methods
- Design: Controlled between-subjects online experiment with six groups: five trust-repair treatments (apology, asking questions, local explanations, counterfactual options, no TRS) plus a no-error control group.
- Sample/context: Recruited on Prolific from adults in Western Europe with fluent English, at least 95% task approval, and prior online shopping experience; the scenario was an e-commerce customer service interaction about a missing item.
- Analysis: Used Kruskal-Wallis tests, Dunn’s post-hoc tests with Bonferroni correction, Mann-Whitney U tests, and chi-square tests of independence; normality was not satisfied, so the authors used nonparametric tests.
## Limitations
- The authors state external validity is limited because the study was conducted in a customer service / e-commerce context, and results may not transfer to higher-stakes domains such as healthcare or finance.
- The design captures only a single interaction in a controlled setting; the paper says this is a limitation because real trust is shaped by cumulative interactions and longitudinal or field studies are needed.
- The study used a single LLM (Gemini 2.0 Flash) and text-only interactions, which the authors say limits generalizability and does not capture the role of visual or multimodal explanations.
- Evident from the text: the continuance decision was based on a deceptive fictitious second task, which may limit ecological validity; the paper itself notes that actual continuance could be influenced by the artificial constraints of the experimental setting.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
14 Valid · 3 Not valid · 10 Not checked · 84 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Furthermore, users' primary focus is usually on obtaining the desired outcome efficiently, prioritizing resolution over understanding of why a failure occurred (Collier et al., 2017;Hassija et al., 2024).”
What the sources say
- Not checked — no full text of the sourcecites Collier et al., 2017 source
- Partly supportedcites Hassija et al., 2024 sourceExperimental — accuracy not yet measured
In “Are Explanations Always Important?” (page unavailable), the review reports that users perceived some systems positively despite receiving no reasoning for their predictions. That supports the idea that explanations are not always users’ priority, but it does not establish that users usually prioritize efficiently resolving a failure over understanding its cause. (LLM, conf=0.77)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Users might lack the technical expertise or motivation to decipher technical information such as inference scores for system decisions (Abusitta et al., 2024;Liao et al., 2020).”
What the sources say
- Not checked — no full text of the sourcecites Abusitta et al., 2024 source
- Supportedcites Liao et al., 2020 source
In the Performance section (page unavailable), the paper says numerical ML metrics can be hard for lay users to interpret, and that performance information ranked lowest especially for users without an AI background and in less critical decisions. It also reports that users struggle to understand whether confidence scores are useful for their decisions. Together, these passages support the claim's qualified point about expertise and motivation to interpret technical scores. (LLM, conf=0.86)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In such scenarios, technical explanations might be perceived as irrelevant or even obstructive if they do not directly facilitate problem resolution or provide the reassurance users seek after interaction errors (Ali et al., 2023;Chander et al., 2025).”
What the sources say
- Partly supportedcites Ali et al., 2023 sourceExperimental — accuracy not yet measured
Section 1.3, “Future Solutions” (page unavailable), argues that explanations should be judged by whether they meet users’ needs for a given task, supporting the concern that a technical explanation may not be useful to a user. Section 1.2 also says explanation quality depends on the person interpreting it. Neither passage addresses explanations being perceived as obstructive or users seeking reassurance after interaction errors. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites Chander et al., 2025 source
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“However, a limitation in current XAI research is its predominant focus on ex-ante trust formation or calibration.”
What the sources say
- Could not verifycites Ali et al., 2023 sourceExperimental — accuracy not yet measured
Sections 1.2 (Challenges and Limitations) and 1.3 (Future Solutions) describe XAI evaluations as method-centered rather than sufficiently human-centered. They do not address whether current XAI research predominantly focuses on ex-ante trust formation or calibration. Searches for those terms found no decisive passage; page numbers are unavailable in our copy. (LLM, conf=0.72)
- Not checked — no full text of the sourcecites Chander et al., 2025 source
- Could not verifycites Kowald et al., 2024 sourceExperimental — accuracy not yet measured
Section 3.3 describes XAI as relevant throughout design, development, and deployment, including enhancing user trust, but does not characterize where current XAI research predominantly focuses. Section 4 says most trustworthy-AI evaluation schemes are static; that is not a finding about ex-ante trust formation or calibration in XAI research. Searches for those terms found no passage establishing the claimed predominance. (LLM, conf=0.73)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Despite the conceptual tension between”
What the sources say
- Supportedcites Harland et al., 2025 source
Section 4.6.1.2 reports some comparisons involving human-like and machine-like AI agents but says their effects are not fully understood and calls for further research. Section 4.6.2 finds few applied technical studies implementing AI apology autonomously. Together, these support the claim that comparative empirical evidence remains limited, particularly for repair carried out by the AI system itself. (LLM, conf=0.86)
- Not matchedcites Poser et al., 2023
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
66 more claims · 6 with their cited sources checked
Create a free account to see all 111 claims and to verify the 3 references still open.
- It may state two separate claims as one. 19
- Probably not a substantial claim. 24
- The quote only partly states this claim. 1
Statistics recomputed
Every reported test result, recomputed from its test statistic and degrees of freedom. A result shows as not adding up only once an independent check has confirmed it.
- Consistentχ²(5) = 30.33reported p < .001 · recomputed p < .001
“χ2 (5, N = 261) = 30.33,p < .001”
- Consistentχ²(1) = 10.89reported p < .001 · recomputed p < .001
“χ2 (1, N = 174) = 10.89,p < .001”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Self-check results appear here once an independent check has confirmed them.
Citations
Cites
Statistical Power Analysis for the Behavioral Sciences
Cohen, J. (2013) · doi:10.4324/9780203771587 · Cited by 25,373
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736
Not So Different After All: A Cross-Discipline View Of Trust
Rousseau, D. M., Sitkin, S. B., Burt, R. S., & Camerer, C. (1998) · Academy of Management Review · doi:10.5465/amr.1998.926617 · Cited by 10,274
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 4,688
Human trust in artificial intelligence: Review of empirical research
Glikson, E., & Woolley, A. W. (2020) · Academy of Management Annals · doi:10.5465/annals.2018.0057 · Cited by 2,921
Trust in Automation: Integrating Empirical Evidence on Factors That Influence Trust
Hoff, K. A., & Bashir, M. (2015) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720814547570 · Cited by 2,817
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024) · Cognitive Computation · doi:10.1007/s12559-023-10179-8 · Cited by 2,495
Nass, C., Steuer, J., & Tauber, E. R. (1994) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/191666.191703 · Cited by 2,148
Research works printed but not linked: 3
- Benner, D [D.], Elshan, E., Sofia, S., & Janson, A [A.]. (2021). What do you mean? A review on recovery strategies to overcome conversational breakdowns of conversational agents. In ICIS 2021 Proceedings.
- Diederich, S., Janßen-Müller, M., Brendel, A. B., & Morana, S. (2019). Emulating empathetic behavior in online service encounters with sentiment-adaptive responses: Insights from an experiment with a conversational agent. In International Conference on Information Systems (ICIS).
- Tomczak, M., & Tomczak, E. (2014). The need to report effect size estimates revisited. An overview of some recommended measures of effect size. Trends in Sport Sciences, 21(1), 19–25.
Metadata
- Authors
- Konopka, B., & Wiesche, M.
- Affiliations
- TU Dortmund University (DE)
- Corresponding author
- Konopka, Björn
- Venue
- Information Systems Frontiers
- Published
- 2026-06-03
- ISSN
- 1387-3326 (ISSN-L)
- 1572-9419
- OpenAlex
- W7163354529
- Cited by
- 1
- References
- 76
- Citations by year
- 2026: 1
- FWCI
- 3.46
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Information Systems Frontiers (publishedVersion, cc-by)
- Funders
- Technische Universität Dortmund
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Social Sciences › Business, Management and Accounting › Marketing › Customer Service Quality and Loyalty
- Keywords
- explainable AI, trust repair, chatbots, customer service automation, system errors, local explanations, counterfactual explanations, apology, user trust
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Explainability in AI: Comparing Human-Like and System-Like Trust Repair Strategies. https://app.cochat.ai/papers/10.1007/s10796-026-10751-1
- The paper
- Konopka, B., & Wiesche, M. (2026). Explainability in AI: Comparing Human-Like and System-Like Trust Repair Strategies. Information Systems Frontiers. https://doi.org/10.1007/s10796-026-10751-1
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.


