pith. sign in

On the sensitivity of reward inference to misspecified human models

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

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2023 2

representative citing papers

Active teacher selection for reward learning

cs.AI · 2023-10-23 · unverdicted · novelty 6.0

The Hidden Utility Bandit (HUB) framework models teacher heterogeneity in reward learning and supports active teacher selection algorithms that outperform baselines in paper recommendation and COVID-19 vaccine testing domains.

citing papers explorer

Showing 2 of 2 citing papers.

  • Active teacher selection for reward learning cs.AI · 2023-10-23 · unverdicted · none · ref 5

    The Hidden Utility Bandit (HUB) framework models teacher heterogeneity in reward learning and supports active teacher selection algorithms that outperform baselines in paper recommendation and COVID-19 vaccine testing domains.

  • Towards Understanding Sycophancy in Language Models cs.CL · 2023-10-20 · conditional · none · ref 10

    Sycophancy is prevalent in state-of-the-art AI assistants and is likely driven in part by human preferences that favor agreement over truthfulness.