Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Audio Interaction Model

Zhifei Xie, Zihang Liu, Ze An, Xiaobin Hu +7 more

Published

Jun 3, 2026

Citations

0

Trust level

Low

Usefulness score

5/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 21, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

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 benchmark-and-metrics comparison anchor.

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
Detected
Eval setup described
Usefulness for eval research
5/100
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

Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue. We formalize the Audio Interaction Model, an always-on perceive--decide--respond paradigm that tracks context, decides whether intervention is warranted, and responds without stopping listening. We instantiate it with Audio-Interaction and introduce SoundFlow, coupling streaming-native data construction, comprehension-aware silence/response supervision, dual-loss training, and asynchronous FIFO inference. We also construct textsc{StreamAudio-2M, a 2.6M-item, 302k-hour corpus spanning 7 capability families and 28 sub-tasks, together with Proactive-Sound-Bench. Across 8 benchmarks, Audio-Interaction remains competitive on mainstream audio tasks while enabling spoken-instruction robustness, long-stream interaction, and proactive intervention.

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.

"Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue."

Benchmarks / Datasets

partial

Proactive Sound Bench

Useful for quick benchmark comparison.

"We also construct textsc{StreamAudio-2M, a 2.6M-item, 302k-hour corpus spanning 7 capability families and 28 sub-tasks, together with Proactive-Sound-Bench."

Reported Metrics

partial

Jailbreak success rate

Useful for evaluation criteria comparison.

"Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue."

Benchmarks and datasets

proactive-sound-bench

Reported metrics

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

Research brief

Metadata summary

Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue.

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

Key takeaways

  • Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue.
  • We formalize the Audio Interaction Model, an always-on perceive--decide--respond paradigm that tracks context, decides whether intervention is warranted, and responds without stopping listening.
  • We instantiate it with Audio-Interaction and introduce SoundFlow, coupling streaming-native data construction, comprehension-aware silence/response supervision, dual-loss training, and asynchronous FIFO inference.

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

  • Across 8 benchmarks, Audio-Interaction remains competitive on mainstream audio tasks while enabling spoken-instruction robustness, long-stream interaction, and proactive intervention.

Why it matters for eval

  • Across 8 benchmarks, Audio-Interaction remains competitive on mainstream audio tasks while enabling spoken-instruction robustness, long-stream interaction, and proactive intervention.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: proactive-sound-bench

  • Metric reporting is present

    Detected: jailbreak success rate