# Scam Detection Conversational Evaluation on Google Pay India (Pre-Production) Source: [Scam Detection Conversational Evaluation on Google Pay India (Pre-Production)]() Collection index: [llms.txt]() Data updated: 2026-05-04T07:13:51.469Z Evaluation of conversational agent performance focused on Scam Detection within the Google Pay India pre-production environment, measured by metrics like Topic Adherence and User Respect. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Scam Detection Conversational Evaluation | | Dataset (including any stated split) | Google Pay India (Pre-Production) | | Metric | Topic Adherence | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 1 of 1 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Topic Adherence](): Higher is better; unit: PERCENT. - [User Respect](): Higher is better; unit: PERCENT. - [Scam MO Elicitation Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Topic Adherence | Result date | Report paper | | --- | --- | --- | --- | | CASE | 99.9 | Not recorded | 68fa7af91e209131cea860e4 | ### CASE Topic Adherence: 99.9. Result ID: 69f846b947f34ce924db7cc7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Production Stage":"Pre-Prod","Evaluation Protocol":"Human Raters"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.