Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Rubric Semantics or Numerical Priors? Auditing Scale-Direction Bias in LLM Judges

Chanwoo Kim, Doyun Kim, Minsoo Song, Sihyeon Lee +1 more

Published

Nov 19, 2026

Citations

0

Trust level

Moderate

Usefulness score

57/100 (Medium)

Extraction confidence

65% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 19, 2026

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 for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The abstract does not clearly name benchmarks or metrics.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
57/100
Moderate-confidence candidate

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

Abstract

Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges. This paradigm assumes LLMs evaluate based on the rubric's semantic meaning rather than its numeric scale. We question this assumption by introducing semantic faithfulness: the principle that semantically equivalent rubrics must yield consistent scores. To quantify this, we propose a scale-reversal probe that inverts score anchors without altering evaluation criteria. Furthermore, we introduce floor normalization to calibrate reversal disagreement against intrinsic model variability, enabling fair cross-model comparisons. Experiments across five meta-evaluation benchmarks with seven diverse LLM judges spanning open-weight and proprietary models reveal widespread violations of semantic faithfulness, showing that raw reversal agreement alone is misleading. Finally, we demonstrate that bidirectional anchor averaging reduces dependence on any single anchor direction without compromising alignment with human judgments. Our findings emphasize that trustworthy LLM judges must reliably follow rubric semantics, not just correlate with human ratings.

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

Rubric Rating

Directly usable for protocol triage.

"Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges."

Evaluation Modes

strong

Llm As Judge

Includes extracted eval setup.

"Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

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

Research brief

Metadata summary

Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges.

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

Key takeaways

  • Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges.
  • This paradigm assumes LLMs evaluate based on the rubric's semantic meaning rather than its numeric scale.
  • We question this assumption by introducing semantic faithfulness: the principle that semantically equivalent rubrics must yield consistent scores.

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.

Contribution summary

  • Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges.
  • This paradigm assumes LLMs evaluate based on the rubric's semantic meaning rather than its numeric scale.

Why it matters for eval

  • To quantify this, we propose a scale-reversal probe that inverts score anchors without altering evaluation criteria.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: 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

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.