ThreatCore is a new benchmark showing implicit threats are much harder for models to detect than explicit ones, with semantic role labeling helping by clarifying intent structure.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.
The paper introduces the Construct Validity Protocol to validate semantic embeddings for social constructs and proposes Counterfactual Neutralization using LLMs to reduce confounding.
citing papers explorer
-
ThreatCore: A Benchmark for Explicit and Implicit Threat Detection
ThreatCore is a new benchmark showing implicit threats are much harder for models to detect than explicit ones, with semantic role labeling helping by clarifying intent structure.
-
DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift
DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.
-
The Proxy Presumption: From Semantic Embeddings to Valid Social Measures
The paper introduces the Construct Validity Protocol to validate semantic embeddings for social constructs and proposes Counterfactual Neutralization using LLMs to reduce confounding.