Q003¶


Research	R0044 — Expanded Vocabulary Research
Run	2026-04-01
Query	Q003

Query: Has anyone in the regulated industries (aviation, defense, healthcare, finance) published research or guidance that explicitly connects the human-factors concept of "automation bias" or "overtrust" to the AI safety concept of "sycophancy"? Is anyone bridging these two vocabularies?

BLUF: No publication explicitly and deliberately bridges these vocabularies. Ibrahim et al. (2025) come closest, using both automation bias and sycophancy in a unified overreliance framework. The CSET brief bridges structurally. But a formal vocabulary mapping has not been published. Most researchers remain in one tradition or the other, as exemplified by sycophancy technical surveys that make no reference to human factors research.

Probability: N/A (open-ended query) | Confidence: Medium

Summary¶

Entity	Description
Query Definition	Query text, scope, status
Assessment	Full analytical product with reasoning chain
ACH Matrix	Evidence x hypotheses diagnosticity analysis
Self-Audit	ROBIS-adapted 5-domain audit (process + source verification)

Hypotheses¶

ID	Hypothesis	Status
H1	Formal vocabulary bridge exists	Eliminated
H2	Partial/functional bridge exists	Supported
H3	No bridging at all	Eliminated

Searches¶

ID	Target	Results	Selected
S01	Direct bridge search	10	2
S02	Overreliance as bridging concept	10	1

Sources¶

Source	Description	Reliability	Relevance
SRC01	Ibrahim et al. overreliance	Medium-High	High
SRC02	CSET automation bias	High	Medium-High
SRC03	Malmqvist sycophancy survey	Medium	Medium

Original Contribution Opportunity¶

The absence of a formal vocabulary mapping between human factors (automation bias, overtrust, complacency, commission error, alert fatigue) and AI safety (sycophancy, RLHF-induced agreement, reward hacking) represents an opportunity for original contribution. Such a mapping would help regulated industries leverage decades of human factors research when addressing AI sycophancy.

Revisit Triggers¶

Publication of a formal vocabulary mapping between human factors and AI safety
Ibrahim et al. paper appearing in peer-reviewed journal
Conference sessions dedicated to cross-disciplinary bridging (e.g., CHI, AAAI, HFES)
Regulated-industry standards body (EASA, FDA, FINRA) adopting AI safety vocabulary