LLM agents autonomously evolve human-readable safety specifications from sparse 1-bit danger signals, outperforming reward-based reflection that encourages reward hacking.
Inverse reward design
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Survey experiment finds that people apply more deontological standards to AI described as human-programmed and to the programmers themselves than to unaided humans or unprogrammed robots in a moral dilemma.
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
-
Discovering Agentic Safety Specifications from 1-Bit Danger Signals
LLM agents autonomously evolve human-readable safety specifications from sparse 1-bit danger signals, outperforming reward-based reflection that encourages reward hacking.