passdrill
AI & LLM Engineering · Evaluation, Testing & Safety · Card 009/010 easy

A public platform for comparing chatbot quality shows users two anonymous model responses to the same prompt side by side and asks only 'which response is better,' rather than asking users to rate each response independently on, say, a 1-5 scale. The platform then aggregates these pairwise votes into a single ranking (an Elo-style rating) for each model. Why is this pairwise-comparison approach generally considered more reliable than collecting independent absolute ratings for ranking relative model quality?

  1. Relative judgments -- deciding which of two responses is better -- are generally easier for humans to make consistently than assigning an absolute numeric score, so pairwise comparisons tend to produce less noisy, better-calibrated signal for ranking models against each other than independently-collected absolute ratings, which vary more across raters and over time
  2. Absolute ratings are mathematically impossible to aggregate across different raters, while pairwise comparisons require no aggregation step at all before a ranking can be produced
  3. Pairwise comparisons take less time for the platform to collect than absolute ratings, and evaluation validity is determined entirely by how many total votes are collected, regardless of how the question is framed
  4. Absolute rating scales are only usable for evaluating machine translation quality specifically, so any other evaluation task must default to pairwise comparison instead
Next card → Shuffle