VEXA: Evidence-Grounded and Persona-Adaptive Explanations for Scam Risk Sensemaking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912879040528384 |
|---|---|
| author | An, Heajun Ng, Connor Dulal, Sandesh Sharma Kim, Junghwan Cho, Jin-Hee |
| author_facet | An, Heajun Ng, Connor Dulal, Sandesh Sharma Kim, Junghwan Cho, Jin-Hee |
| contents | Online scams across email, short message services, and social media increasingly challenge everyday risk assessment, particularly as generative AI enables more fluent and context-aware deception. Although transformer-based detectors achieve strong predictive performance, their explanations are often opaque to non-experts or misaligned with model decisions. We propose VEXA, an evidence-grounded and persona-adaptive framework for generating learner-facing scam explanations by integrating GradientSHAP-based attribution with theory-informed vulnerability personas. Evaluation across multi-channel datasets shows that grounding explanations in detector-derived evidence improves semantic reliability without increasing linguistic complexity, while persona conditioning introduces interpretable stylistic variation without disrupting evidential alignment. These results reveal a key design insight: evidential grounding governs semantic correctness, whereas persona-based adaptation operates at the level of presentation under constraints of faithfulness. Together, VEXA demonstrates the feasibility of persona-adaptive, evidence-grounded explanations and provides design guidance for trustworthy, learner-facing security explanations in non-formal contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05056 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VEXA: Evidence-Grounded and Persona-Adaptive Explanations for Scam Risk Sensemaking An, Heajun Ng, Connor Dulal, Sandesh Sharma Kim, Junghwan Cho, Jin-Hee Cryptography and Security Computation and Language Machine Learning Online scams across email, short message services, and social media increasingly challenge everyday risk assessment, particularly as generative AI enables more fluent and context-aware deception. Although transformer-based detectors achieve strong predictive performance, their explanations are often opaque to non-experts or misaligned with model decisions. We propose VEXA, an evidence-grounded and persona-adaptive framework for generating learner-facing scam explanations by integrating GradientSHAP-based attribution with theory-informed vulnerability personas. Evaluation across multi-channel datasets shows that grounding explanations in detector-derived evidence improves semantic reliability without increasing linguistic complexity, while persona conditioning introduces interpretable stylistic variation without disrupting evidential alignment. These results reveal a key design insight: evidential grounding governs semantic correctness, whereas persona-based adaptation operates at the level of presentation under constraints of faithfulness. Together, VEXA demonstrates the feasibility of persona-adaptive, evidence-grounded explanations and provides design guidance for trustworthy, learner-facing security explanations in non-formal contexts. |
| title | VEXA: Evidence-Grounded and Persona-Adaptive Explanations for Scam Risk Sensemaking |
| topic | Cryptography and Security Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2602.05056 |