Skip to content
← Back to explorer

When LLM Judge Scores Look Good but Best-of-N Decisions Fail

Eddie Landesberg · Mar 12, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Provisional trust

This page is a lightweight research summary built from the abstract and metadata while deeper extraction catches up.

Best use

Background context only

What to verify

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

Evidence quality

Provisional

Derived from abstract and metadata only.

Abstract

Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels. This can be misleading when the real deployment task is best-of-n selection within a prompt. In a 5,000-prompt best-of-4 benchmark from Chatbot Arena, a judge with moderate global correlation (r = 0.47) captures only 21.0% of the improvement that perfect selection would achieve over random choice. The gap arises because global agreement is driven largely by prompt-level baseline effects, while selection depends on within-prompt ranking: within-prompt correlation is only r_within = 0.27, and coarse pointwise scoring creates ties in 67% of pairwise comparisons. In a matched-pair best-of-2 audit, explicit pairwise judging recovers much of this lost signal, raising recovery from 21.1% to 61.2%. For judge-based selection, the relevant audit should report within-prompt signal, tie rates, and recovery/top-1 accuracy, not global agreement alone.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

  • This page is still relying on abstract and metadata signals, not a fuller protocol read.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

Signal extraction is still processing. This page currently shows metadata-first guidance until structured protocol fields are ready.

Best use

Background context only

Use if you need

A provisional background reference while structured extraction finishes.

Main weakness

This page is still relying on abstract and metadata signals, not a fuller protocol read.

Trust level

Provisional

Usefulness score

Unavailable

Eval-fit score is unavailable until extraction completes.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

Usefulness for eval research

Provisional (processing)

Extraction confidence 0%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

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

provisional (inferred)

Pairwise preference

Directly usable for protocol triage.

"Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels."

Evaluation Modes

provisional (inferred)

Automatic metrics

Includes extracted eval setup.

"Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels."

Quality Controls

provisional (inferred)

Not reported

No explicit QC controls found.

"Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels."

Benchmarks / Datasets

provisional (inferred)

Not extracted

No benchmark anchors detected.

"Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels."

Reported Metrics

provisional (inferred)

Accuracy, Agreement / Kappa

Useful for evaluation criteria comparison.

"For judge-based selection, the relevant audit should report within-prompt signal, tie rates, and recovery/top-1 accuracy, not global agreement alone."

Rater Population

provisional (inferred)

Unknown

Rater source not explicitly reported.

"Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels."

Human Feedback Details

This page is using abstract-level cues only right now. Treat the signals below as provisional.

  • Potential human-data signal: Pairwise preference
  • Potential benchmark anchors: No benchmark names detected in abstract.
  • Abstract highlights: 3 key sentence(s) extracted below.

Evaluation Details

Evaluation fields are inferred from the abstract only.

  • Potential evaluation modes: Automatic metrics
  • Potential metric signals: Accuracy, Agreement / Kappa
  • Confidence: Provisional (metadata-only fallback).

Research Brief

Metadata summary

Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels.

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

Key Takeaways

  • Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels.
  • This can be misleading when the real deployment task is best-of-n selection within a prompt.
  • In a 5,000-prompt best-of-4 benchmark from Chatbot Arena, a judge with moderate global correlation (r = 0.47) captures only 21.0% of the improvement that perfect selection would achieve over random choice.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • 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.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

No related papers found for this item yet.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Create Account & Post a Job
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
Learn About Managed Service
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.
Join Now