Pith. sign in

Research agenda for sociotechnical approaches to ai safety

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Interpreting Language Reward Models via Contrastive Explanations

cs.LG · 2024-11-25 · conditional · novelty 5.0

Reward model preferences can be explained by generating counterfactual and semifactual answer variations along 15 hand-picked evaluation attributes and measuring which attribute changes flip the model's preference.

citing papers explorer

Showing 1 of 1 citing paper.

  • Interpreting Language Reward Models via Contrastive Explanations cs.LG · 2024-11-25 · conditional · none · ref 8

    Reward model preferences can be explained by generating counterfactual and semifactual answer variations along 15 hand-picked evaluation attributes and measuring which attribute changes flip the model's preference.