swapping-candidate-order-alone-can-flip-judges-preferencemechanismsingle paper
Swapping candidate order alone can flip the judge's preference, so an evaluator can be gamed by ordering.
Capability: Biased when judging other outputs
Sources
- Swapping candidate order alone can flip the judge's preference, so an evaluator can be gamed by ordering.
Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.
Related claims
- As a raw pairwise judge with no order-swap mitigation, GPT-4 can have its verdict flipped simply by swapping which candidate answer is shown first; applying a position-swap protocol restores agreement with careful human raters to close to human-human agreement levels.Biased when judging other outputs