Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Blind Spots Travel, Knowledge Stays Home: What RL Inherits from an LLM Judge

Liang Yue, Eric A. Vance

Published

Nov 18, 2026

Citations

0

Trust level

Low

Usefulness score

37/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 18, 2026

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

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

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
37/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

Abstract

LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model. In 814 RL runs that teach 7-8B models to answer closed-book questions or abstain, we ask what passes. What a grader knows about single answers stays home. A wrong answer that a judge rewards is memorised for that one question. A model trained with the answer key, or with a far stronger judge, chooses which new questions to answer no better than the untrained model does by sampling 32 answers and abstaining where they disagree; the grader's knowledge adds about one corrected answer per hundred questions. What a grader believes about a kind of question travels. A judge that rejects eleven of the twelve correct training answers about capitals of former states teaches the model to refuse 98% of such capitals on new questions, a loss that accuracy and abstention rates do not reveal. Changing only those twelve verdicts by hand moves the refusal from 5% to 90%, even for a grader that accepts as many answers as the answer key; at that leniency, two of four judges already cost 38-42% of these capitals. The capitals are not forgotten: with "I don't know" blocked, the model answers 94% of them correctly. The grader therefore needs no knowledge of its own: rewarding the model for giving the answer that most of its own untrained samples agree on, with no labels and no judge, earns the answer key's reward and keeps the category.

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

missing

None explicit

No explicit feedback protocol extracted.

"LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model."

Evaluation Modes

partial

Llm As Judge, Automatic Metrics

Includes extracted eval setup.

"LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model."

Quality Controls

missing

Not reported

No explicit QC controls found.

"LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model."

Reported Metrics

partial

Accuracy

Useful for evaluation criteria comparison.

"A judge that rejects eleven of the twelve correct training answers about capitals of former states teaches the model to refuse 98% of such capitals on new questions, a loss that accuracy and abstention rates do not reveal."

Benchmarks and datasets

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

Reported metrics

accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Llm As Judge, Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model.

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

Key takeaways

  • LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model.
  • In 814 RL runs that teach 7-8B models to answer closed-book questions or abstain, we ask what passes.
  • What a grader knows about single answers stays home.

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.

Recommended queries

Contribution summary

  • LLM judges serve as rewards where no answer key exists, in the hope that their knowledge passes to the trained model.
  • In 814 RL runs that teach 7-8B models to answer closed-book questions or abstain, we ask what passes.

Why it matters for eval

  • A wrong answer that a judge rewards is memorised for that one question.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Llm As Judge, Automatic Metrics

  • 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

    Detected: accuracy