Introduces NormBench benchmark and Span-Grounded Deontic Trees (SG-DT) for defeasible scope parsing to reduce Silent Scope Omission in LLMs on statutes and policies.
arXiv preprint arXiv:2511.12001 (2025) 3
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Across 9 VLMs and 9,000 pairs, 72.9% of cases show Visual Sycophancy (split beliefs: vision preserved, wrong answer decoded), zero show robust refusal, and scale worsens the pattern while cutting language shortcuts.
Explanation preferences for AI privacy redaction vary systematically with domain and redaction amount; giving users their preferred styles raises trust over random or no explanations.
citing papers explorer
-
From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing
Introduces NormBench benchmark and Span-Grounded Deontic Trees (SG-DT) for defeasible scope parsing to reduce Silent Scope Omission in LLMs on statutes and policies.
-
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
Across 9 VLMs and 9,000 pairs, 72.9% of cases show Visual Sycophancy (split beliefs: vision preserved, wrong answer decoded), zero show robust refusal, and scale worsens the pattern while cutting language shortcuts.
-
Exploring the Interaction of Explanation Styles, Context, and Trust of AI Privacy Redaction in AI-mediated Interactions
Explanation preferences for AI privacy redaction vary systematically with domain and redaction amount; giving users their preferred styles raises trust over random or no explanations.