Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures

David Nordfors

Published

Jun 19, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

25% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Aug 20, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

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

Background context only.

What to verify

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

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
0/100
Adjacent candidate

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

If you are doing eval pipeline work, start here

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

Abstract

We present evidence that analogy is at the core of LLM intelligence. In our benchmark, LLMs compete in generating sets of analogous statements and rate each other's sets on their own understandings of factual correctness, beauty, intelligence, distinctness, length, and structural diversity. Nothing enters from outside: the only given is the game rules; every item is generated in play; the scores come from the players' ratings alone. Ground truth is replaced by the SVD of the factual rating matrix, which scores players as generators and judges at once -- to our knowledge the first eigen-equation that judges the judges for an LLM council-of-peers. For subjective criteria like beauty, judges are weighted by their rating consistency. The best generators turn out to be middling judges. GPQA Diamond -- difficult multiple-choice questions written by human experts -- could not be more different in method, yet the two benchmarks correlate at Pearson $r = 0.97$, 95% CI [0.92, 0.99]; no leakage could be found. A council of the five best issues the official ratings; its contestable seats let the benchmark scale to any number of players and rise with the models it measures -- a candidate steering signal for self-improving AI. Playing interweaves at least eight constructs of intelligence; the total scores the broad composite, the components allow reductionistic analysis. Every number recomputes from a released package at https://github.com/dnordfors/metanym-game-paper

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.

"We present evidence that analogy is at the core of LLM intelligence."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"We present evidence that analogy is at the core of LLM intelligence."

Quality Controls

missing

Not reported

No explicit QC controls found.

"We present evidence that analogy is at the core of LLM intelligence."

Benchmarks / Datasets

partial

GPQA

Useful for quick benchmark comparison.

"GPQA Diamond -- difficult multiple-choice questions written by human experts -- could not be more different in method, yet the two benchmarks correlate at Pearson $r = 0.97$, 95% CI [0.92, 0.99]; no leakage could be found."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"We present evidence that analogy is at the core of LLM intelligence."

Rater Population

partial

Domain Experts

Helpful for staffing comparability.

"GPQA Diamond -- difficult multiple-choice questions written by human experts -- could not be more different in method, yet the two benchmarks correlate at Pearson $r = 0.97$, 95% CI [0.92, 0.99]; no leakage could be found."

Benchmarks and datasets

GPQA

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Domain Experts
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

We present evidence that analogy is at the core of LLM intelligence.

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

Key takeaways

  • We present evidence that analogy is at the core of LLM intelligence.
  • In our benchmark, LLMs compete in generating sets of analogous statements and rate each other's sets on their own understandings of factual correctness, beauty, intelligence, distinctness, length, and structural diversity.
  • Nothing enters from outside: the only given is the game rules; every item is generated in play; the scores come from the players' ratings alone.

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

Contribution summary

  • We present evidence that analogy is at the core of LLM intelligence.
  • In our benchmark, LLMs compete in generating sets of analogous statements and rate each other's sets on their own understandings of factual correctness, beauty, intelligence, distinctness, length, and structural diversity.
  • GPQA Diamond -- difficult multiple-choice questions written by human experts -- could not be more different in method, yet the two benchmarks correlate at Pearson r = 0.97, 95% CI [0.92, 0.99]; no leakage could be found.

Why it matters for eval

  • In our benchmark, LLMs compete in generating sets of analogous statements and rate each other's sets on their own understandings of factual correctness, beauty, intelligence, distinctness, length, and structural diversity.
  • GPQA Diamond -- difficult multiple-choice questions written by human experts -- could not be more different in method, yet the two benchmarks correlate at Pearson r = 0.97, 95% CI [0.92, 0.99]; no leakage could be found.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: GPQA

  • Metric reporting is present

    No metric terms extracted.