Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Self-Preference Bias in Rubric-Based Evaluation of Large Language Models

José Pombal, Ricardo Rei, André F. T. Martins

Published

Apr 8, 2026

Citations

0

Trust level

High

Usefulness score

67/100 (Medium)

Extraction confidence

75% (High)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Apr 8, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Llm As Judge Medicine Pairwise Preference Rubric Rating

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this as a practical starting point for protocol research, then validate against the original paper.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
67/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

LLM-as-a-judge has become the de facto approach for evaluating LLM outputs. However, judges are known to exhibit self-preference bias (SPB): they tend to favor outputs produced by themselves or by models from their own family. This skews evaluations and, thus, hinders model development, especially in settings of recursive self-improvement. We present the first study of SPB in rubric-based evaluation, an increasingly popular benchmarking paradigm where judges issue binary verdicts on individual evaluation criteria, instead of assigning holistic scores or rankings. Using IFEval, a benchmark with programmatically verifiable rubrics, we show that SPB persists even when evaluation criteria are entirely objective: among rubrics where generators fail, judges can be up to 50\% more likely to incorrectly mark them as satisfied when the output is their own. We also find that, similarly to other evaluation paradigms, ensembling multiple judges helps mitigate SPB, but without fully eliminating it. On HealthBench, a medical chat benchmark with subjective rubrics, we observe that SPB skews model scores by up to 10 points, a potentially decisive margin when ranking frontier models. We analyze the factors that drive SPB in this setting, finding that negative rubrics, extreme rubric lengths, and subjective topics like emergency referrals are particularly susceptible.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Pairwise Preference, Rubric Rating

Directly usable for protocol triage.

"LLM-as-a-judge has become the de facto approach for evaluating LLM outputs."

Evaluation Modes

strong

Llm As Judge

Includes extracted eval setup.

"LLM-as-a-judge has become the de facto approach for evaluating LLM outputs."

Quality Controls

missing

Not reported

No explicit QC controls found.

"LLM-as-a-judge has become the de facto approach for evaluating LLM outputs."

Benchmarks / Datasets

strong

IFEval, Healthbench

Useful for quick benchmark comparison.

"Using IFEval, a benchmark with programmatically verifiable rubrics, we show that SPB persists even when evaluation criteria are entirely objective: among rubrics where generators fail, judges can be up to 50\% more likely to incorrectly mark them as satisfied when the output is their own."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"LLM-as-a-judge has become the de facto approach for evaluating LLM outputs."

Benchmarks and datasets

IFEvalHealthbench

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Pairwise Preference, Rubric Rating
Rater population
Not reported
Unit of annotation
Multi Dim Rubric
Expertise required
Medicine
Evaluation details
Evaluation modes
Llm As Judge
Agentic eval
None
Quality controls
Not reported
Evidence quality
High
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

LLM-as-a-judge has become the de facto approach for evaluating LLM outputs.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • LLM-as-a-judge has become the de facto approach for evaluating LLM outputs.
  • However, judges are known to exhibit self-preference bias (SPB): they tend to favor outputs produced by themselves or by models from their own family.
  • This skews evaluations and, thus, hinders model development, especially in settings of recursive self-improvement.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Pairwise preference evaluation Rubric rating evaluation

Contribution summary

  • LLM-as-a-judge has become the de facto approach for evaluating LLM outputs.
  • We present the first study of SPB in rubric-based evaluation, an increasingly popular benchmarking paradigm where judges issue binary verdicts on individual evaluation criteria, instead of assigning holistic scores or rankings.
  • Using IFEval, a benchmark with programmatically verifiable rubrics, we show that SPB persists even when evaluation criteria are entirely objective: among rubrics where generators fail, judges can be up to 50\% more likely to incorrectly…

Why it matters for eval

  • We present the first study of SPB in rubric-based evaluation, an increasingly popular benchmarking paradigm where judges issue binary verdicts on individual evaluation criteria, instead of assigning holistic scores or rankings.
  • Using IFEval, a benchmark with programmatically verifiable rubrics, we show that SPB persists even when evaluation criteria are entirely objective: among rubrics where generators fail, judges can be up to 50\% more likely to incorrectly…

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference, Rubric Rating

  • Evaluation mode is explicit

    Detected: Llm As Judge

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: IFEval, Healthbench

  • Metric reporting is present

    No metric terms extracted.