Find up to n entries that most strongly contradict theme X, drawn from the entries shown in the prompt (supporting entries plus the bounded candidate sample of non-theme corpus entries). Same extractive shape as counter_narrative.
Usage
provoke_disconfirming_evidence(
theme_name,
theme_entries,
data,
provider,
n = 5L,
audit_log = NULL,
response_cache = NULL,
fabrication_log = NULL
)Arguments
- theme_name
Character: the theme to challenge.
- theme_entries
Tibble: entries the researcher believes support the theme (must have std_id and std_text).
- data
Tibble: the full corpus. Used to resolve and verify cited entry_ids (T0.1) and to draw the bounded candidate sample of non-theme entries for the counter-evidence categories; the model is NOT given the full corpus to search.
- provider
AIProvider object.
- n
Integer: maximum provocations to return (default 5).
- audit_log
Optional AuditLog.
- response_cache
Optional ResponseCache.
- fabrication_log
Optional FabricationLog.