Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Dec 202419922001200920172026
1 result for “POWER-DL”
Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hackingcs.LG

Paper addresses reward hacking in preference optimization, proposing POWER-DL to improve AI alignment.

problem Reward hacking problem in preference optimization, leading to undesired behaviors.
method POWER-DL combines robust reward maximization and dynamic label updates to mitigate reward hacking.
result POWER-DL consistently outperforms state-of-the-art methods on alignment benchmarks.
reward hackingpreference optimizationAI alignmentPOWER-DLdynamic labels
2024-12-12abs ↗pdf ↗