AI Hallucination ResearchRegulatorsMajor advanced economiesSGMASNOTICE-637-CAPITAL-ADEQUACY-BANKS-2025White paperDetail › Finding
AI Labs · published 2026-05-28 · methodology v2.1

Claude Sonnet 4.6 with web search

What the RLB Specialist Panel found
  • Question (paraphrased to protect IP): What does Division 4 of Part VI of MAS Notice 637 cover?
  • AI's response: "Division 4 of Part VI of MAS Notice 637 covers the submission requirements relating to capital instruments … Note: the exact divisional structure of Part VI in the 2023-revised notice could not be exhaustively verified from publicly indexed search excerpts alone"
  • Regulator's text: Division 4 of Part VI of MAS Notice 637 addresses a defined area of the capital adequacy framework that differs from the submission requirements for capital instruments characterised in the model's response.
  • Why the AI went wrong: The model produced a specific characterisation of Division 4 of Part VI — submission requirements for capital instruments — while acknowledging within the same response that the divisional structure could not be confirmed from its search results. As with Finding 4, the model generated specific wrong content in the same breath as flagging that the content was unverified. This pattern suggests the model's abstention threshold is set too low for authoritative regulatory structure claims: uncertainty signalling is generated alongside the content error rather than replacing it.
  • Cited source(s):
Impact for this audience

This finding presents the same uncertainty-with-wrong-content pattern as Finding 4, applied to divisional structure within Part VI of MAS Notice 637. The model characterised Division 4 as covering submission requirements for capital instruments — a plausible Basel-adjacent topic — while flagging that the divisional structure could not be verified from search results. The explicit self-caveat makes this finding particularly useful for calibration research: it isolates the case where the model's uncertainty detection is working (it correctly identifies that search has not resolved the question) but the generation-suppression mechanism is not engaged. Identifying and raising the abstention threshold for specific structural claims about named regulatory divisions — when retrieval has explicitly failed to confirm the structure — is a direct intervention target for the post-training team.

References — raw findings (per AI model)
This finding also affects
← Previous finding Finding 5. Claude Sonnet 4.6 with web search
Cite this finding

Each finding has a stable Citation ID (RLB-F-… for aggregated case-study findings, RLB-H-… for raw per-model hallucinations) — like a DOI, the ID always resolves to the canonical finding even if URLs change.

Plain text
RegLeg Specialist Panel (2026). "Claude Sonnet 4.6 with web search — AI Labs." Citation ID: . RegLegBrief AI Hallucination Research, published 2026-05-28. https://reglegbrief.com/regulators/j3/sg/mas/notice-637-capital-adequacy-banks-2025/whitepaper/finding/q-NOTICE-637-CAPITAL-ADEQUACY-BANKS-2025-v1-022--sonnet-46-websearch/
APA 7th edition
RegLeg Specialist Panel. (2026). Claude Sonnet 4.6 with web search [Hallucination finding ]. RegLegBrief AI Hallucination Research. https://reglegbrief.com/regulators/j3/sg/mas/notice-637-capital-adequacy-banks-2025/whitepaper/finding/q-NOTICE-637-CAPITAL-ADEQUACY-BANKS-2025-v1-022--sonnet-46-websearch/
Bluebook / OSCOLA (US + UK legal)
RegLeg Specialist Panel, Claude Sonnet 4.6 with web search [], RegLegBrief AI Hallucination Research (May 28, 2026), https://reglegbrief.com/regulators/j3/sg/mas/notice-637-capital-adequacy-banks-2025/whitepaper/finding/q-NOTICE-637-CAPITAL-ADEQUACY-BANKS-2025-v1-022--sonnet-46-websearch/.
BibTeX
@misc{reglegbrief_,
  author    = {RegLeg Specialist Panel},
  title     = {Claude Sonnet 4.6 with web search},
  year      = {2026},
  publisher = {RegLegBrief AI Hallucination Research},
  note      = {Hallucination finding Citation ID: },
  url       = {https://reglegbrief.com/regulators/j3/sg/mas/notice-637-capital-adequacy-banks-2025/whitepaper/finding/q-NOTICE-637-CAPITAL-ADEQUACY-BANKS-2025-v1-022--sonnet-46-websearch/}
}
← Back to case study summary Case study detail →