Similar Items: Generating Statistical Charts with Validation-Driven LLM Workflows
- U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
- When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels
- Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
- Steer Like the LLM: Activation Steering that Mimics Prompting
- Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers
- Unsupervised Machine Learning for Detecting Structural Anomalies in European Regional Statistics