Language switching caused by malformed training data—model fixates on spurious cues inferring user's non-native status, detected via NLA representations preceding foreign-language output.

{
  "doc": "natural.md",
  "context": "Case study demonstrating NLA ability to surface root causes of model misbehavior; corroborated by training data inspection.",
  "category": "ai",
  "norm_label": "Language switching caused by malformed training data—model fixates on spurious cues inferring user's non-native status, detected via NLA representations preceding foreign-language output.",
  "graphify_id": "language_switching_finding",
  "source_file": "natural.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/natural/graph.json",
  "extracted_type": "finding",
  "source_location": "§Language Switching",
  "graphify_file_type": "finding"
}