ALAS: An Automatic Latent Alignment Score for Audio Language Models

arXiv:2505.19937 · cs.CL, cs.SD, eess.AS · Submitted 2025-05-26 · Read on arXiv

cs.CL, cs.SD, eess.AS

Submitted: 2025-05-26

Updated: 2026-09-27

Comments: Accepted to IEEE MLSP 2026

Code: https://github.com/poonehmousavi/alas979-8-3503-2411-2

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 57× in this paper
• Accuracy — 12× in this paper · explained in 1 episode
• Benchmark — 9× in this paper · explained in 2 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Model-Agnostic — 4× in this paper · explained in 2 episodes
• Automatic Latent Alignment Score — 3× in this paper
• Grounding — 3× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 8 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Spoken Language Understanding — 2× in this paper
• Calibration — 1× in this paper · explained in 7 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Instruction Tuning — 1× in this paper · explained in 3 episodes

Sources

• LLaMA: Open and Efficient Foundation Language Models
• Qwen2-Audio Technical Report
• Discrete Audio Tokens: More Than a Survey!
• A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
• Gemini: A Family of Highly Capable Multimodal Models
• AudioPaLM: A Large Language Model That Can Speak and Listen
• Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data
• Eureka-Audio: Triggering Audio Intelligence in Compact Language Models
• SSR: Alignment-Aware Modality Connector for Speech Language Models
• Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition
• AudioBench: A Universal Benchmark for Audio Large Language Models
• LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models
• MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark
• Qwen2.5-Omni Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering