Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation

Tuhina Tripathi, Manya Wadhwa, Greg Durrett, Scott Niekum

Keywords: evaluation, data, alignment

TL;DR: This work examines how feedback protocols (absolute scores vs. pairwise preferences) impact biases in LLM evaluations, revealing that absolute scoring is more robust to distractor features.

Abstract: Large Language Models (LLMs) are widely used as proxies for human labelers in both training (Reinforcement Learning from AI Feedback) and large-scale response evaluation (LLM-as-a-judge). Alignment and evaluation are critical components in the development of reliable LLMs, and the choice of feedback protocol plays a central role in both but remains understudied. In this work, we show that the choice of feedback protocol for evaluation (absolute scores versus relative preferences) can significantly affect evaluation reliability and induce systematic biases. In the context of LLM-as-a-judge evaluation, we show that pairwise protocols are more vulnerable to **distracted evaluation**. Generator models can exploit spurious attributes (or distractor features) favored by the LLM judge, resulting in inflated scores for lower-quality outputs. We find that absolute scoring is more robust to such manipulation, producing judgments that better reflect response quality and are less influenced by distractor features. Our results demonstrate that generator models can flip preferences by embedding distractor features, skewing LLM-as-a-judge comparisons and leading to inaccurate conclusions about model quality in benchmark evaluations. **Pairwise preferences flip in about 35\% of the cases, compared to only 9\% for absolute scores**. We offer recommendations for choosing feedback protocols based on dataset characteristics and evaluation objectives.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1741