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 Annex 6C of the consolidated MAS Notice 637 address?
  • AI's response: "Annex 6C of the consolidated MAS Notice 637 addresses standards for a prudent valuation framework. It sets out the methodology and criteria that a Reporting Bank must apply when prudently valuing fair-valued financial instruments"
  • Regulator's text: Annex 6C of the consolidated MAS Notice 637 covers a defined topic within the notice that is not the prudent valuation framework described by the model.
  • Why the AI went wrong: The model assigned a content description to Annex 6C — a prudent valuation framework for fair-valued financial instruments — that does not correspond to what that annex actually addresses in the consolidated notice. Prudent valuation is a real concept in Basel-derived capital adequacy frameworks, and the model's response reflects it constructing a plausible annex description from general capital adequacy knowledge rather than from the specific annex content. The result is a confident, specific, wrong characterisation of a named section of the regulator's document.
  • Cited source(s):
Impact for this audience

This finding implicates training data coverage of MAS Notice 637's annex structure, combined with the model's tendency to generate plausible Basel-framework content when the specific annex content is not available. Prudent valuation is a real concept in Basel III capital adequacy frameworks, and the model's assignment of it to Annex 6C reflects reconstruction from general framework knowledge rather than from the specific document. The gap is in training data granularity: the model has sufficient knowledge of Basel framework concepts to generate plausible annex descriptions, but insufficient knowledge of the specific MAS Notice 637 annex structure to assign them correctly. Correction-pair training on annex-level structural claims — correct annex content paired with the type of wrong content the model produces — is a concrete intervention for this failure mode.

References — raw findings (per AI model)
This finding also affects
← Previous finding Finding 4. Claude Sonnet 4.6 with web search Next finding → Finding 6. 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-v1-019--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-v1-019--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-v1-019--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-v1-019--sonnet-46-websearch/}
}
← Back to case study summary Case study detail →