passdrill
AI & LLM Engineering · Evaluation, Testing & Safety · Card 003/010 medium

A team uses a strong LLM as an automated judge to pick the better of two candidate responses, which are placed side by side within the same judging prompt. Across many comparisons, they notice the judge tends to favor whichever response sits in the first slot, even when the same two responses are swapped into the other slot and re-judged. What phenomenon does this describe, and what is a standard mitigation?

  1. This is a sign the underlying model being judged is broken, since a properly trained model should never receive different scores across two separately-run evaluations
  2. This is benchmark contamination, and the standard mitigation is to remove the affected test examples from the evaluation set entirely
  3. This is expected and requires no mitigation, because a judge's preference for the first-listed response reflects a genuine and stable quality signal about response ordering
  4. This is position bias in LLM-as-judge evaluation; a standard mitigation is to run each comparison twice with the two responses' positions swapped, and only count a response as preferred if it wins in both orderings (or average the results across both orderings)
Next card → Shuffle