Multi-objective genetic prompt optimization creates multi-turn deceptive datasets validated by humans, then detected with 0.89 recall using angular coverage, distance ratio, and linearity features in embeddings.
Targen: Targeted data genera- tion with large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Mid-training LLMs on self-generated diverse reasoning paths improves subsequent RL performance on mathematical benchmarks and OOD tasks.
citing papers explorer
-
Evolving and Detecting Multi-Turn Deception using Geometric Signatures
Multi-objective genetic prompt optimization creates multi-turn deceptive datasets validated by humans, then detected with 0.89 recall using angular coverage, distance ratio, and linearity features in embeddings.
-
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Mid-training LLMs on self-generated diverse reasoning paths improves subsequent RL performance on mathematical benchmarks and OOD tasks.