Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades
Edoardo Pona, Milad Kazemi, Mehran Hosseini +4
Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive exper…
cs.LG2026
Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
Wei Liu, Siya Qi, Yali Du +1
Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are better understood as self-play and often p…