Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

CoTTAGE: An Explainable Judge for Text-to-Audio Generation

Yu-Xiang Lin, Yun-Man Hsu, Bo-Ru Lu, Kuan-Po Huang +10 more

Published

Nov 13, 2026

Citations

0

Trust level

Moderate

Usefulness score

67/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 13, 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

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.

Abstract

Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation. However, existing metrics fail to simultaneously deliver high correlation with human judgments and meaningful, audio-grounded explanations, forcing reliance on labor-intensive human evaluation that bottlenecks model development iteration. To address this, we propose CoTTAGE, a reasoning-based evaluator for text relevance (REL) and audio quality (OVL). Following a reason-then-predict paradigm, CoTTAGE first generates an audio-grounded rationale to diagnose errors before predicting scores. Supported by over 10K newly collected human OVL annotations, CoTTAGE is first trained via supervised fine-tuning and then refined with reinforcement learning using a Thurstone-based preference objective that converts sampled score distributions into pairwise preference probabilities and rewards agreement with rankings derived from human judgments. Across six benchmarks spanning REL and OVL, CoTTAGE achieves state-of-the-art correlation with human judgments while producing human-preferred explanations to accelerate TTA development.

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

Directly usable for protocol triage.

"Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation."

Evaluation Modes

strong

Human Eval

Includes extracted eval setup.

"Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation."

Reported Metrics

strong

Agreement

Useful for evaluation criteria comparison.

"Supported by over 10K newly collected human OVL annotations, CoTTAGE is first trained via supervised fine-tuning and then refined with reinforcement learning using a Thurstone-based preference objective that converts sampled score distributions into pairwise preference probabilities and rewards agreement with rankings derived from human judgments."

Benchmarks and datasets

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

Reported metrics

agreement
Human feedback details
Uses human feedback
Yes
Feedback types
Pairwise Preference
Rater population
Not reported
Unit of annotation
Pairwise
Expertise required
General
Evaluation details
Evaluation modes
Human Eval
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation.

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

Key takeaways

  • Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation.
  • However, existing metrics fail to simultaneously deliver high correlation with human judgments and meaningful, audio-grounded explanations, forcing reliance on labor-intensive human evaluation that bottlenecks model development iteration.
  • To address this, we propose CoTTAGE, a reasoning-based evaluator for text relevance (REL) and audio quality (OVL).

Researcher actions

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

Contribution summary

  • Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation.
  • However, existing metrics fail to simultaneously deliver high correlation with human judgments and meaningful, audio-grounded explanations, forcing reliance on labor-intensive human evaluation that bottlenecks model development iteration.

Why it matters for eval

  • Across six benchmarks spanning REL and OVL, CoTTAGE achieves state-of-the-art correlation with human judgments while producing human-preferred explanations to accelerate TTA development.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Evaluation mode is explicit

    Detected: Human Eval

  • 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: agreement