AI
FraudBench: Stress-Testing Policy-Grounded Banking Agents Against Adaptive Fraud
Researchers have introduced FraudBench, a benchmark designed to test the safety of policy-grounded b...
AI
Efficient Adaptation of LLMs for Hate Speech Detection in Low-Resource Languages: A Comparative Study on Roman Urdu
Researchers have developed a method to improve the detection of hate speech in Roman Urdu, a low-res...
AI
RDFdL: Integrating RDF with Differential Dynamic Logic
Researchers have proposed a framework called RDFdL that combines knowledge graphs with differential ...
AI
Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
Researchers propose Adversarial Review (AR), a protocol for cooperative code review where three agen...
AI
Looped Language Models Improve Compositional Tool Calling
Researchers have developed looped language models to improve the ability of AI s...
AI
On the Triangle Inequality for the Jaccard Distance in Arbitrary Lattices
Researchers have made new theoretical discoveries about the Jaccard distance in ...
AI
GenEx: A Graph-Based Representational Paradigm for SARS-CoV-2 Variant Detection via Codon Co-occurrence Networks
Researchers have developed a new method for detecting SARS-CoV-2 variants called...
AI
Redakto - The Incognito Tab for LLMs
Researchers have developed a tool called Redakto to anonymize text before it's f...