Sycophancy is a boundary failure between social alignment and epistemic integrity, captured by a three-condition framework plus taxonomy of targets, mechanisms, and severity.
From Hallucination to Scheming: A Unified Taxonomy and Benchmark Analysis for LLM Deception
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Large language models (LLMs) produce systematically misleading outputs, from hallucinated citations to strategic deception of evaluators, yet these phenomena are studied by separate communities with incompatible terminology. We propose a unified taxonomy organized along three complementary dimensions: degree of goal-directedness (behavioral to strategic deception), object of deception, and mechanism (fabrication, omission, or pragmatic distortion). Applying this taxonomy to 50 existing benchmarks reveals that every benchmark tests fabrication while pragmatic distortion, attribution, and capability self-knowledge remain critically under-covered, and strategic deception benchmarks are nascent. We offer concrete recommendations for developers and regulators, including a minimal reporting template for positioning future work within our framework.
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
Sycophancy is a boundary failure between social alignment and epistemic integrity, captured by a three-condition framework plus taxonomy of targets, mechanisms, and severity.