arXiv AI
LURE: a Phase-Labelled Synthetic Corpus of Online-Grooming Exchanges
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 15
Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection
arXiv:2606.27314v2 Announce Type: replace Abstract: To avoid moderation and surveillance on social media, some users routinely invent indirect linguistic expressions (ILE) that camouflage sensitive m...
arXiv AI
Jul 15
Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking
arXiv:2607. 12085v1 Announce Type: new Abstract: Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality.
arXiv AI
Aug 20
CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence
CTIFoundry is an agent‑native corpus scaffold designed to improve cyber threat intelligence (CTI) investigations by LLM agents. It transforms traditional CTI data—such as CVE, CWE, CAPEC, and ATT&CK—into a deterministic ontology graph with typed, traversable edges, a span‑grounded report layer that resolves entity aliases and provenance, and hybrid dense‑plus‑lexical retrieval surfaces. When integrated with a standard open‑source agent harness, CTIFoundry boosts overall F1 scores by 0.19 to 0.28 on the CTIConnect benchmark, achieving higher accuracy with fewer tool calls compared to agents using flat, retrieval‑augmented corpora.
arXiv Computation and Language
Sep 22
Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection
The paper introduces a diagnostic tool for distinguishing the use of misogynistic slurs from their mention in counter‑speech within code‑mixed Hinglish. It identifies evaluation artifacts in existing corpora, releases a 416‑item minimal‑pair contrast set that decorrelates slur presence and gendered register from labels, and proposes a pair‑consistency metric to assess model performance. Experiments show that even strong baselines struggle to consistently label counter‑speech pairs, while a large language model achieves perfect scores, indicating the benchmark measures genuine capability rather than exploitation of artifacts.
arXiv AI
Aug 12
ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls
arXiv:2608. 11200v1 Announce Type: cross Abstract: Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are difficult to access, release, or annotate.
arXiv Computation and Language
Sep 15
SlopShape: Identifying AI-Generated Commercial Web Content
arXiv:2609.15369v1 Announce Type: new Abstract: Word-level detectors identify unedited AI-generated text almost perfectly, but the literature documents their brittleness under rewording, and a word-l...