Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge

Jisu Jeon, Seungyeon Jwa, Joosung Lee, Jinhyeon Kim +5 more

Published

Jun 23, 2026

Citations

0

Trust level

High

Usefulness score

77/100 (High)

Extraction confidence

85% (High)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Jun 23, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

General Llm As Judge Pairwise Preference

Should you rely on this paper?

This paper has strong direct human-feedback and evaluation protocol signal and is suitable as a primary eval pipeline reference.

Use this as a practical starting point for protocol research, then validate against the original paper.

Best use

Primary benchmark and eval reference

Use if you need

A concrete protocol example with enough signal to inform rater workflow design.

What to verify

Validate the exact study setup 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
77/100
High-confidence candidate

Use this as a primary source when designing or comparing eval protocols.

If you are doing eval pipeline work, start here

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

Abstract

Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech. However, prior approaches predominantly focus on holistic naturalness, leaving fine-grained paralinguistic distinctions underexplored. We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender. Our experiments show that current LALM judges still lag behind human judgments by 32%p on average and exhibit severe calibration failures, particularly in Tie cases where the correct decision is to abstain. To further analyze lexical versus acoustic reliance, the benchmark includes both same-transcript and cross-transcript conditions. ParaPairAudioBench enables multi-dimensional, calibration-aware assessment of the reliability of LALM-as-a-Judge for paralinguistic speech evaluation.

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.

"Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech."

Evaluation Modes

strong

Llm As Judge

Includes extracted eval setup.

"Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech."

Quality Controls

strong

Calibration

Calibration/adjudication style controls detected.

"Our experiments show that current LALM judges still lag behind human judgments by 32%p on average and exhibit severe calibration failures, particularly in Tie cases where the correct decision is to abstain."

Benchmarks / Datasets

strong

Parapairaudiobench

Useful for quick benchmark comparison.

"We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech."

Benchmarks and datasets

Parapairaudiobench

Reported metrics

No metric terms were extracted from the available abstract.

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
Llm As Judge
Agentic eval
None
Quality controls
Calibration
Evidence quality
High
Use this page as
Primary benchmark and eval reference

Research brief

Metadata summary

Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech.

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

Key takeaways

  • Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech.
  • However, prior approaches predominantly focus on holistic naturalness, leaving fine-grained paralinguistic distinctions underexplored.
  • We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender.

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

Pairwise preference evaluation Calibration

Contribution summary

  • Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech.
  • We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender.
  • Our experiments show that current LALM judges still lag behind human judgments by 32%p on average and exhibit severe calibration failures, particularly in Tie cases where the correct decision is to abstain.

Why it matters for eval

  • We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender.
  • Our experiments show that current LALM judges still lag behind human judgments by 32%p on average and exhibit severe calibration failures, particularly in Tie cases where the correct decision is to abstain.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Evaluation mode is explicit

    Detected: Llm As Judge

  • Quality control reporting appears

    Detected: Calibration

  • Benchmark or dataset anchors are present

    Detected: Parapairaudiobench

  • Metric reporting is present

    No metric terms extracted.