Evaluation + Rag + Llm

38.0

Develop a lightweight framework for auditing AI hallucination patterns using synthetic datasets of fake news or medical facts. This helps in benchmarking model susceptibility to misinformation.

+96

emergingimplementation gap

evaluationsafetytruthfulnessragllminference

Signals (10)

arXiv10h ago

CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data

arXiv10h ago

Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation

YHN1d ago

Evaluation + Rag + Llm

Signals (10)

CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data

TEMPER: Testing Emotional Perturbation in Quantitative Reasoning

ATANT: An Evaluation Framework for AI Continuity

Scientists invented a fake disease. AI told people it was real

Claude mixes up who said what and that's not OK

Google's AI Overviews spew false answers per hour, bombshell study reveals

Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models

ConvApparel: Measuring and bridging the realism gap in user simulators

Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation

AMD AI director says Claude Code is becoming dumber and lazier since update