Similar Items: U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
- Generating Statistical Charts with Validation-Driven LLM Workflows
- On the Hardness of Junking LLMs
- Verifier-Backed Hard Problem Generation for Mathematical Reasoning
- Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
- Steer Like the LLM: Activation Steering that Mimics Prompting
- Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML