Papers with Large Audio-Language Models

11 papers
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for audio-centric interaction have impeded advancements in this field . AIR-Bench evaluates LALMs' ability to understand audio signals and interact with humans .
Approach: They propose a benchmark to evaluate the ability of large audio-language models to understand audio signals . they use 19 tasks with approximately 19k single-choice questions to examine single-task ability .
Outcome: The proposed framework evaluates the ability of large audio-language models to understand audio signals and interact with humans in the textual format.
Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Audio-Language Models (LALMs) have recently unlocked audio dialogue capabilities, enabling direct spoken exchanges with humans.
Approach: They propose to evaluate LALMs' open-ended audio dialogue ability in 3 general scenarios, 12 skills, 9 multilingual languages, and 4 categories of ambiguity handling.
Outcome: The proposed benchmark assesses the open-ended audio dialogue ability for LALMs in 3 general scenarios, 12 skills, 9 multilingual languages, and 4 categories of ambiguity handling.
When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large Audio-Language Models (LALMs) are augmented with the ability to perceive audio, but their reliability when faced with conflicting inputs remains largely unexplored.
Approach: They examine how LALMs prioritize information when presented with inconsistent audio-text pairs.
Outcome: The proposed models display a significant bias toward textual input when presented with inconsistent audio-text pairs.
Extending Audio Context for Long-Form Understanding in Large Audio-Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Prior work has introduced context-extension methods (e.g. YaRN) on unimodal LLMs, yet their application to LALMs remains unexplored.
Approach: They propose a training-free, modality-decoupled extension method that modifies only audio token positions, leaving text positions intact to preserve the base LLM’s text capabilities.
Outcome: The proposed method outperforms the original models across wide range of settings and provides significant performance improvement on long audio of unseen lengths.
SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues? (2026.acl-long)

Copied to clipboard

Challenge: Large Audio-Language Models (LALMs) are a popular approach for evaluating speech quality, yet their ability to assess speaker consistency across multi-turn dialogues remains unexplored.
Approach: They construct 1,818 human-verified evaluation instances across four datasets spanning synthetic and real speech, with controlled acoustic difficulty.
Outcome: The proposed model performs better in comparing and ranking acoustic variants, demonstrating inherent acustic discrimination capabilities.
Pardon? Evaluating Conversational Repair in Large Audio-Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluations of large audio-language models focus on answer accuracy and robustness to acoustic perturbations, but they assume that inputs remain semantically answerable.
Approach: They propose a repair-aware evaluation setting that explicitly distinguishes between answerable and unanswerable audio inputs.
Outcome: The proposed evaluation setting distinguishes between answerable and unanswerable audio inputs.
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models (2026.acl-long)

Copied to clipboard

Challenge: a recent study evaluated large audio-language models against jailbreak attacks . a new benchmark is being developed to evaluate LAM safety against jailbreaking attacks based on temporal and semantic nature of speech .
Approach: They propose a benchmark to evaluate LAM jailbreak vulnerabilities in adversarial audio prompts . they use a dataset of 1,495 adversarials to evaluate their performance .
Outcome: The proposed benchmark evaluates state-of-the-art LAMs against jailbreak attacks . it demonstrates that even small, semantically preserved perturbations can reduce safety .
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study (2025.emnlp-main)

Copied to clipboard

Challenge: Large Audio-Language Models (LALMs) are increasingly being deployed in real-world applications, yet their robustness against malicious audio injection remains underexplored.
Approach: They quantitatively assess their vulnerabilities and resilience using metrics: the Defense Success Rate, Context Robustness Score, and Judgment Robustic Index.
Outcome: The proposed models demonstrate significant performance disparities across four attack scenarios.
AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives (2026.findings-acl)

Copied to clipboard

Challenge: Large Audio-Language Models suffer from hallucinations, e.g., generating text not grounded in the audio input.
Approach: They propose a framework to address hallucination problems in large audio-language models . they use a preference dataset to test the model's accuracy .
Outcome: The proposed model outperforms the latest SOTA methods in terms of performance and generalization.
HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on hallucination focus on text or vision, while few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth.
Approach: They propose a large-scale benchmark for evaluating hallucinations across speech, sound, and music.
Outcome: The proposed model improves hallucination rate, yes/no bias, error-type analysis, and refusal rate.
CliniCAST: Benchmarking Acoustic Grounding and Text Dominance in Medical Triage (2026.findings-acl)

Copied to clipboard

Challenge: Recent Large Audio-Language Models (LALMs) integrate acoustic capabilities into reasoning, yet whether they reliably ground clinical judgments in audible evidence remains unproven.
Approach: They propose a benchmark that disentangles clinically meaningful acoustic cues from lexical content and speaker demographics.
Outcome: Evaluating 5,856 synthetic samples across 12 disease conditions, the proposed model exhibits fragile acoustic grounding and pronounced "text dominance" failure mode.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations