pith. sign in

The singapore consensus on global ai safety research priorities

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.LG 1

years

2025 2

verdicts

UNVERDICTED 2

representative citing papers

Failure Modes of Maximum Entropy RLHF

cs.LG · 2025-09-24 · unverdicted · novelty 5.0

Derives SimPO from MaxEnt RL and reports that MaxEnt RL in online RLHF exhibits frequent overoptimization and unstable KL dynamics across scales, unlike stable KL-constrained baselines.

citing papers explorer

Showing 2 of 2 citing papers.

  • From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails cs.AI · 2025-10-15 · unverdicted · none · ref 12

    Control-theoretic guardrails enable proactive correction of risky LLM agent actions in latent space, preventing catastrophes like collisions or bankruptcy while preserving task performance in simulated environments.

  • Failure Modes of Maximum Entropy RLHF cs.LG · 2025-09-24 · unverdicted · none · ref 9

    Derives SimPO from MaxEnt RL and reports that MaxEnt RL in online RLHF exhibits frequent overoptimization and unstable KL dynamics across scales, unlike stable KL-constrained baselines.