Large Audio Language Models

Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio representations into a large language model (LLM) backbone to enable multimodal reasoning. Recent test-time reinforcement learning (TTRL) methods further improve LLM reasoning capability by leveraging unlabelled test data after pre-training. However, the importance of the perceptual capability of LALMs remains underexplored, particularly how much acoustic evidence is integrated and relied upon during reasoning, and how this contributes to final task performance. This gap limits the development of effective post-training methods like TTRL for audio reasoning. In this work, we first analyse how audio information is integrated and utilised during reasoning process. We quantify layer-wise perceptual reliance and show that stronger acoustic reliance is associated with higher accuracy and a larger performance gain attributable to the audio input. Building on this, we propose Perception-Grounded TTRL (PG-TTRL), which aligns label-free test-time optimisation with perceptually grounded reasoning, encouraging the model to structure its reasoning more strongly on the audio input. Experiments across LALMs and benchmarks show that PG-TTRL consistently improves reasoning performance over both the base models and standard TTRL, showing the value of perceptual-grounding optimisation for test-time audio reasoning.

Long-form audio performance is often summarized by context length and aggregate accuracy, obscuring how language, evidence, and task jointly shape difficulty. We introduce MuLA-Bench: 5,038 open-ended questions over 1,769 in-the-wild recordings totaling 1,377.9 hours, covering 16 languages and eight domains. A balanced Language x Domain semantic track supports controlled comparisons, while a complementary acoustic track preserves naturally occurring non-speech evidence. Evidence-grounded generation, shortcut checks, and language-expert review provide auditable questions without translating a shared source set or injecting target sounds. We evaluate ten audio-language models and conduct pooled diagnostics on a fixed eight-model cohort. Language rankings change across domains and tasks; acoustic-semantic performance gaps vary with the requested operation; and temporal errors can persist after the correct event is identified. Long-range retrieval is comparatively strong, while precise clock alignment and factual grounding of natural acoustic events remain fragile. MuLA-Bench thus exposes conditional failure patterns that a single long-context score does not capture.

Multi-encoder fusion extends Large Audio-Language Models (LALMs) beyond speech-centric recognition, but selecting encoders via intuition or exhaustive search often introduces redundant representations and inflates an already constrained compute budget. We propose CUES (Correlation-gUided Encoder Selection), a lightweight heuristic that estimates complementarity through task- and category-level Pearson correlations between encoders' performance profiles, scoring a candidate set from single-encoder evaluations alone--without fusion training during selection. Evaluated on the XARES-LLM benchmark with a frozen SmolLM2-135M backbone (LoRA-adapted) via five-fold cross-validation, CUES consistently identifies the same configuration per track from held-out development splits alone, without using test data for selection. For the broad TrackA suite, CUES selects a cross-family trio (Whisper-medium, mHuBERT-147, and Dasheng-base), achieving a 4.3% relative gain over Whisper-medium (0.771 vs. 0.739). For TrackB text generation, it re-anchors on a focused, speech-only pair (mHuBERT-147 and WavLM-base-plus) and actively abstains from adding a divergent encoder, outperforming mHuBERT-147 by 6.3% (0.589 vs. 0.554). Rather than a failure to scale, this divergence is consistent with a diversity--interference trade-off that CUES navigates per track from correlation signals alone: across the evaluated pool, added cross-family diversity tends toward an inverted-U on broad audio tasks but toward steady degradation on text generation, which favors a focused, speech-anchored set.

Large Audio-Language Models (LALMs) have substantially advanced general audio understanding, yet they remain limited in fine-grained temporal perception, particularly in precise event localization. Existing approaches primarily post-train LALMs to predict event boundaries as timestamp tokens. However, this generative formulation lacks explicit correspondence between the timestamp predictions and fine-grained acoustic evidence, limiting the precision and reliability of temporal localization. To address this issue, we augment the LALM with a dedicated frame-level grounding model while leveraging its semantic modeling capability to represent the event query. Specifically, the frozen LALM encodes the event query with audio as context, and the grounding model combines these query representations with fine-grained audio features to localize the target event at the frame level. Extensive experiments across diverse temporal grounding benchmarks demonstrate strong and consistent improvements over existing methods. Further evaluation shows that the grounding model can provide temporal evidence to support downstream reasoning.

Empathetic response generation in spoken dialogue systems requires both accurate emotion perception and appropriate emotion regulation. Grounded in psychological theories such as the Perception-Action Model and emotion regulation theory, effective empathy depends not only on inferring a user's affective state but also on regulating how it is expressed in responses. However, recent large audio-language models (LALMs) largely treat emotion as a direct conditioning signal, lacking explicit regulatory mechanisms, which often leads to affect mirroring rather than calibrated support. We propose ER-EDF, a psychology-grounded framework that explicitly decouples emotion perception and emotion regulation in LALMs. Perception tracks the user's emotional state, while regulation determines how this state should guide empathetic response generation. The framework is model-agnostic and integrates seamlessly into existing LALMs. We further construct a spoken empathetic dialogue dataset and introduce empathy-aware evaluation metrics beyond lexical matching. Experiments across five LALMs and two datasets show that ER-EDF consistently improves empathetic response quality in both automatic and human evaluations, highlighting the importance of jointly modeling emotion perception and regulation in spoken empathetic dialogue systems, paving a new direction for psychologically grounded empathetic AI.

Human speech includes nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, which convey affective and interactional information. Existing approaches typically represent NVVs as transcript-level tags, providing limited supervision for their waveform-time boundaries. We present NVV-Locator for fine-grained NVV temporal grounding. We first unify 26 NVV categories across public resources and construct large-scale timestamp-supervised training data through dual-LLM verification, transcript-guided forced alignment, and energy-based boundary refinement. We further introduce NVV-TimeBench, an expert-refined benchmark with 667 utterances and 1,094 events. NVV-Locator uses a non-autoregressive slot-filling architecture to jointly predict lexical timestamps, NVV categories, and event boundaries. On NVV-TimeBench, it achieves 71.0% Micro F1, 70.2% Macro F1, 80.4% Macro mIoU, and 59.6 ms Macro mMAE, outperforming the evaluated large audio model counterparts. Evaluation on an external corpus further demonstrates the cross-corpus generalization of NVV-Locator.

Large Audio Language Models (LALMs) have shown strong performance on audio reasoning benchmarks, but accuracy alone cannot distinguish true reasoning from superficial pattern matching, often overestimating reasoning ability since high scores may result from guessing rather than genuine audio understanding. Evaluating the reasoning process itself is essential for improving LALMs' reasoning ability, yet remains challenging. Existing methods either rely on costly human annotation or opaque LLM-as-judge approaches, making them impractical, biased, and lacking transparency. Moreover, audio reasoning introduces unique challenges absent in text-based settings, perceptual hallucination and cross-modal alignment between audio understanding and textual inference, hence text-based evaluation frameworks cannot be directly applied. Therefore, we propose ARIA-Rubrics (Audio Reasoning Integrity Assessment), a lightweight, annotation-free gold reasoning chains, automatic and transparent framework comprising six complementary metrics that evaluate audio reasoning quality across perceptual grounding, reasoning coherence, and answer consistency. We use Chain-of-Thought prompting as an externalization mechanism to make the reasoning process observable. Experiments on 9 models across 2 benchmarks identify three reasoning modes of current LALMs with actionable directions for future development, with ARIA-Rubrics achieving high correlation with human judgments. The code is available at the Github Repository.

Large audio-language models (LALMs) can hallucinate audio objects, answering "yes" to absent sound events, thus undermining reliability in audio question answering. We propose Token-Adaptive Decoding (TAD), a training-free strategy for hallucination mitigation that grounds the initial yes/no decision by contrasting logits under real audio with a matched silent reference. TAD introduces a token-adaptive, confidence-guided gate that is decision-critical at the first decoding step and class-conditional on affirmative tokens, using the audio-silent margin to avoid overcorrection when evidence is weak or already sufficient. Experiments on AudioCaps-Hallucination show that, relative to Audio-Aware Decoding (AAD), a contrastive baseline with fixed contrast strength, TAD improves F1 for Qwen2 by 0.059 to 0.117 across Popular, Adversarial, and Random splits, and for Gemma by 0.025 to 0.064, while on Clotho-AQA it raises F1 from 0.810 to 0.816 on Qwen2 and remains comparable to AAD on Gemma.

Audio language models are designed to understand speech, yet it remains unclear whether they capture how something is said beyond what is said. We present a mechanistic analysis of paralinguistic information in four open source models, Whisper-large-v2, Qwen2-Audio-7B Instruct, Qwen2.5-Omni-7B, and Chroma-4B, using the Expresso dataset with controlled speaking styles. We combine centered kernel alignment, linear probing with leave one speaker out evaluation, open ended tone prediction, and a content prosody leakage metric to trace how style information moves from the audio encoder to the final output. All models strongly encode speaking style in the late encoder, that is, the top third of the audio encoder's layers, but this information is consistently degraded before reaching the output. The projector reshapes representation geometry without removing information, while decoders differ in how much style they preserve depending on architecture and training objective. At the output level, models fall into two behaviors. Some are content driven, where predictions depend mainly on text. Others are acoustic driven, where predictions vary with speaking style. The leakage metric quantifies this difference, and qualitative results confirm it. Overall, we identify a gap between what models encode and what they use, highlighting a key limitation in current audio language models.

With the growing scale of multi-agent architectures and large language models, deployed AI assistants are increasingly tasked with reasoning over long, continuous, multi-session conversation histories. Current benchmarks evaluate this dialogue history as information retrieval over long horizon, temporal reasoning, or knowledge updates, while crucially ignoring the fundamental dynamics of human-agent interaction, i.e. how they said it. To address this gap, we present VoiceLongMemEval (VLME) benchmark, where every answer depends on paralinguistic metadata (emotion labels, prosody descriptors, and voice events) attached to conversational turns, which is otherwise unrecoverable from the words alone. Every item passes a three-stage adversarial gate, ensuring that a strong language model fails when given only the transcript. Evaluating leading frontier and open-weight models reveals a pervasive affect gap; providing text-track paralinguistic metadata yields a 0.09 to 0.38 accuracy boost (0.61 to 0.69 when prompted with evidence hints), while standard ASR pipelines systematically discard this signal. Additionally, audio-native models successfully extract these cues directly from speech (0.354 to 0.412 vs. 0.325 blind). Code and dataset will be made available upon acceptance.

Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify. Despite being essential for downstream tasks like speech recognition and dense audio captioning, timestamping remains a key limitation of most LALMs. We present TEMPO (Temporally-grounded Multi-task Post-training), the first unified model to handle audio, speech, and music timestamping tasks. Our core contribution is a supervised fine-tuning (SFT) stage built on three innovations: atomic timestamp tokens, a time-aware projector that injects sinusoidal wall-clock encodings into audio frame embeddings, and a distance-aware Gaussian loss. Our training is based on a synthetic-to-real curriculum. We further introduce, to our knowledge, the first application of reinforcement learning to unified audio timestamping, using GRPO with verifiable temporal rewards that directly optimize the evaluation objectives. Rather than serving as the primary source of performance gains, GRPO acts as a refinement stage on top of the SFT checkpoint, providing modest additional improvements. To support this work, we build a training dataset containing 119K samples and an evaluation benchmark containing 10K samples, drawn from established corpora across five tasks. On this benchmark, TEMPO outperforms Audio Flamingo Next and Qwen3-Omni, two state-of-the-art LALMs explicitly trained on timestamped data. Experiments confirm that SFT delivers most of these gains, with GRPO providing consistent but moderate refinements.

Speech and audio LLMs are often evaluated by asking whether a waveform prompt beats an automatic speech recognition (ASR) transcript. For known closed-set tasks, that comparison conflates two factors: access to acoustic evidence and the need to call a generative audio model. We evaluate this distinction as a controlled call-decision problem. For each example, a policy chooses among keeping a transcript label, using encoder evidence from Contrastive Language-Audio Pretraining (CLAP), Audio Spectrogram Transformer (AST), or WavLM, and calling Qwen2-Audio, Qwen2.5-Omni, or MOSS-Audio; the decisive ablation removes all generative actions while keeping the selector and development protocol fixed. On VocalSound, transcripts reach 0.296 accuracy, so waveform information is needed. Yet supervised CLAP and WavLM controls reach 0.850 and 0.854 with no generative audio calls. A selector with generative actions reaches 0.925 accuracy using 12.5% calls, compared with 0.921 for the matched no-call selector (paired difference 0.004; 95% CI [-0.025,0.033]). Agreement and stacking features improve weaker selectors but do not beat the strongest no-call control. For known-task endpoint claims, the relevant quantity is the marginal value of the generative call after transcript and encoder evidence have already been used.

General audio comprehension now covers speech, sound, and music over durations from seconds to hours, driven by large audio-language models (LALMs) that are increasingly omni-modal. Yet the benchmarks that test them still rely on clips of seconds, where scores saturate and models converge; recent long-form efforts extend duration but evaluate long audio much as short clips are. We introduce LongAudioSpan, a benchmark that spans both duration and depth: it pairs audio from 10 minutes to over 2 hours with 3,240 questions across three cognitive levels, namely perception, understanding, and reasoning. Two paths supply the questions, differing in how question content is sourced and how ground truth is obtained. Native QA extracts questions from the audio's content, posing each as a multiple-choice item and an open-ended one graded by detailed rubrics. Anchor QA instead injects ground truth, planting acoustic anchors into the audio and building a perception-to-reasoning chain scored only to the first error. A fully automated pipeline constructs every item through structured captioning, QA generation, and adversarial critic feedback. Evaluating 12 LALMs on LongAudioSpan, we find the hard part comes before reasoning: distilling a few relevant facts from a long, redundant signal. This difficulty grows with audio length and falls hardest on perception, especially temporal grounding. LongAudioSpan is available at https://huggingface.co/datasets/holvan/LongAudioSpan.

Large audio-language models (LALMs) have shown promising progress in understanding speech, music, and general sound events, yet their ability to reason about how audio signals are degraded remains underexplored. Existing benchmarks primarily evaluate semantic understanding, event recognition, or high-level audio reasoning, leaving a basic question unanswered: Do LALMs understand the differences in audio quality? We introduce MRMAD, a Multi-Round Multi-Audio Degradation benchmark for evaluating audio degradation perception and understanding in LALMs. MRMAD spans speech, music, and sound, and frames evaluation as multi-turn dialogues across multiple audio inputs, requiring models to identify types of degradation, compare severity, and perceive corruption changes across turns. Unlike current single-turn audio-language benchmarks, MRMAD evaluates whether LALMs can maintain consistent degradation hypotheses with new evidence and comprehend low-level acoustic phenomena over multi-turn dialogues. Through a systematic evaluation of 18 representative LALMs from non-thinking to reasoning and Omni models, we find that current models often recognize coarse content while failing to diagnose, compare, or reason about degradations reliably. Human evaluations further reveal a significant perception gap between LALMs and human listeners. MRMAD thus exposes a critical yet overlooked aspect of audio-language understanding and provides a diagnostic foundation for building future LALMs that are robust to real-world acoustic conditions.

Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive. We deconstruct "naturalness" into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to construct the first dimension-level meta-evaluation benchmark for TTS, comprising 860 utterances annotated by trained linguist raters. Results from benchmarking four MOS predictors and four Audio-LLM judges reveal that MOS predictors collapse onto acoustic signal quality, while Audio-LLM judges show selective, prompt-dependent detection that does not generalise across all dimensions. Neither class reliably captures a breadth of linguistically structured speech errors. Our dataset, annotation schema, and evaluation code are publicly released to support more targeted and interpretable TTS evaluation.

Large audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs. This diversity includes low-frequency signals that are inaudible to humans but can still enter the model and influence its generation. However, the practical impact of such low-frequency inputs on LALMs remains largely unexplored. In this paper, we propose Intermittent Low-Frequency Lockout (ILL), an inaudible red teaming method that evaluates this risk using a universal waveform template in a black box setting. ILL uses Sentence Attention Scale Estimation to determine active intervals and Frequency Confusion Transfer to construct a low-frequency waveform with continuous phase from corpus spectral variation. To mitigate this risk, we propose Distributional Requery Guard (DRG) to detect low-frequency distribution shifts and conditionally request a second recording for semantic recovery. Across six LALMs and multiple audio understanding tasks, ILL reduces accuracy by up to 67 percentage points while receiving a mean human audibility rating of 1.33, close to 1.17 for clean audio; DRG raises mean attacked accuracy from 28.5% to 46.1% after clean reacquisition. These findings identify a previously overlooked safety risk for LALMs and provide a foundation for future research on robust audio understanding.

Emotion is central to human communication, and its expression varies across languages. Large audio-language models (LALMs) achieve strong performance on multilingual speech tasks, yet it remains unclear whether they encode emotion through language-specific correlations or language-agnostic representations. We present the first neuron-level interpretability study of this question. We define Multilingual Emotion Neurons (MLENs) as functional units exhibiting stable emotional selectivity and aligned causal effects across languages, and introduce Consistency-Regularized Fusion (CR-Fusion) to identify them. Across four modern LALMs and 12 typologically diverse languages, emotion-sensitive neurons identified independently per language show minimal overlap, and additional monolingual identification data saturates quickly without isolating more transferable units, motivating identification from pooled cross-lingual evidence. Causal interventions demonstrate that MLENs identified by CR-Fusion provide more precise and transferable affective control than monolingual neuron sets in both zero-shot and low-resource settings. Leave-one-out ablations further reveal asymmetric transfer: individual identification languages, including low-resource ones, contribute non-redundant evidence, while several low-resource languages benefit most from the resulting cross-lingual transfer. Together, our findings provide the first causal, neuron-level account of how LALMs encode emotion across languages, and establish multilingual neuron identification as an effective mechanism for understanding cross-lingual affective behavior.

Audio-language models (ALMs) are increasingly used as judges for speech-to-speech systems, but a judge that receives audio may not actually use paralinguistic evidence. We introduce counterfactual audits for paralinguistic response evaluation. Each audit item holds the transcript fixed while varying affect, prosody, or the timing of an affective shift, forcing a valid judge to track the audio cue rather than lexical content or response style. We evaluate ALM judges using a native one-context judgment protocol and a contrastive recoverability control, then further decompose each item into its constituent perception and response-mapping skills. This yields useful diagnostic states that identify different sources of judge failures. Across Gemini, GPT, and open audio models, we find that contrastive success often overstates native judge reliability, and that similar aggregate accuracies can hide different failure modes. These results suggest that ALM judges should not be evaluated by accuracy alone, instead requiring thorough behavioral audits before deployment.

Spoken Language Understanding (SLU) is the core component of task-oriented dialogue systems and a pivotal link in achieving seamless human-agent interaction. While traditional SLU can effectively extract user semantics for closed-set tasks after in-domain supervised fine-tuning, it faces significant challenges in leveraging in-context learning for open-domain tasks due to its ambiguous rule definitions. This work proposes Spoken Function Calling (SFC), a novel semantic understanding perspective that optimizes semantic understanding with structured rule definitions, to evolve beyond traditional closed-set SLU. Specifically, we curate and extend a suite of spoken functions based on traditional SLU datasets, construct a multi-agent system to synthesize the SFC-Bench dataset, evaluate the performance of Large Language Models (LLMs) and Large Audio Language Models (LALMs), and enhance the SFC capabilities of LALMs through post-training. Experiments demonstrate that SFC outperforms traditional SLU, substantially enhancing the semantic extraction accuracy for LLMs and LALMs.

Large Audio-Language Models (LALMs) excel at general speech understanding; however, adapting them to fine-grained tasks like Speech Emotion Recognition (SER) remains a significant bottleneck. Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate in flat Euclidean space, and this geometry fails to capture the multi-granularity nature of emotion cues, which range from low-level prosody to high-level semantics. To address this, we propose HyPASE, a hyperbolic PEFT framework for LALM-based SER. HyPASE leverages the Poincare ball model, using the hyperbolic radius as an explicit proxy for representational granularity. The framework consists of two core components: a Hyperbolic Geometric Adapter (HGA) for layer-adaptive weight modulation, and an Emotion-aware Multi-capacity Cross-modal Aggregator (EMCA) that compresses multi-scale features into compact audio prefixes. Empirical results on standard benchmarks show that HyPASE outperforms Euclidean PEFT baselines across all metrics on MELD and achieves a notable Unweighted Accuracy gain on IEMOCAP, particularly in class-imbalanced emotion recognition, with the accompanying slight Weighted Accuracy trade-off reflecting hyperbolic space's geometric prioritization of minority-class representations; furthermore, HyPASE achieves robust zero-shot cross-dataset generalization within a constrained parameter budget. By grounding the adaptation process in hyperbolic geometry, HyPASE offers a highly efficient path for LALM fine-tuning.

What is music style? Though often described using text labels such as "swing," "classical," or "emotional," the real style remains implicit and hidden in concrete music examples. In this paper, we introduce a cross-modal framework that learns implicit music styles from raw audio and applies them to symbolic music generation. Inspired by BLIP-2, our model leverages a Querying Transformer (Q-Former) to extract style representations from a large, pre-trained audio language model (LM), and further applies them to condition a symbolic LM for generating piano arrangements. We adopt a two-stage training strategy: contrastive learning to align auditory style with symbolic expression, followed by generative modeling for music arrangement. Our model generates piano performances jointly conditioned on a lead sheet (content) and a reference audio example (style), enabling controllable and stylistically faithful arrangement. Experiments demonstrate the effectiveness of our approach in piano cover generation, style transfer, and audio-to-MIDI retrieval, achieving substantial improvements in style-aware alignment and music quality.

Complex acoustic problems may require models to perform acoustic operations, interact with external tools and reason over the resulting textual or processed-audio observations rather than answer directly from a fixed audio input. We study such problems as tool-interactive audio reasoning and develop SpeechAgent-R, an audio agent that coordinates its intrinsic multimodal understanding with external skills and tools. To support this capability, we construct HIU-Corpus, comprising 65,492 interaction trajectories and 507.6 hours of audio across 24 tasks, 8 skills and 9 tools. SpeechAgent-R first learns structured interaction behaviors through trajectory-based supervised fine-tuning and then improves its decisions through multi-turn reinforcement learning. We further introduce HIU-Bench to jointly evaluate task performance, interaction quality and generalization to diverse task settings. It contains 1,395 samples across 56 tasks, including in-distribution (ID) and out-of-distribution (OOD) splits with substantial shifts in tool usage and workflow composition. SpeechAgent-R achieves 84.17 on ID tasks and 70.94 on OOD tasks, improving over the base model under the same agent harness by 15.40 and 14.23 points. These results demonstrate that learning skill and tool coordination improves audio agents' ability to handle diverse task settings and adaptive tool interactions.

With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions. Existing evaluations often focus on generation quality or task performance, making it difficult to diagnose information coverage and description reliability. We propose MMAC, a \textbf{M}assive \textbf{M}ulti-dimensional benchmark for \textbf{A}udio \textbf{C}aptioning. MMAC contains 5,638 audio clips from more than 20 data sources, covering 6 capability categories and 15 evaluation dimensions. Given a model-generated caption, MMAC checks whether it mentions relevant information in the target dimension and whether the mentioned content is consistent with the reference label. We evaluate representative open-source and proprietary AudioLLMs. Results show clear differences across evaluation dimensions, information coverage, and description reliability. We will release the MMAC benchmark and evaluation code.

Existing audio forgery detection and localization (AFDL) methods often overfit dataset-specific low-level artifacts, limiting their generalization to subtle, localized, and unseen manipulations. Recent audio large language model (ALLM)-based approaches cast AFDL as question answering but still model forensic evidence implicitly, without linking manipulation cues to predictions. To bridge this gap, we propose ThinkOmni, a reasoning-driven omni-modal large language model that jointly performs explicit forensic reasoning, spoofing detection, and temporal manipulation localization. To enable explicit reasoning supervision, we construct Forensic-Aware Chain-of-Thought (FACoT), a 100K-sample dataset with structured forensic evidence and reasoning annotations. Leveraging FACoT, we introduce Forensic-Aware Modality-Incremental Learning (FMIL), which progressively aligns semantic, acoustic, and spectral-visual representations with the LLM backbone to capture complementary forensic cues. We further propose Forensic-Consistent Multi-task Loss (FCML), which combines weighted cross-entropy with an adaptive localization loss to coordinate reasoning generation, spoofing detection, and temporal localization. Extensive experiments show that ThinkOmni achieves strong cross-dataset generalization in both detection and localization. Code, models, data, and inference examples are available at https://beyond0814.github.io/ThinkOmni/.

Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains unclear how much jailbreak capability can arise from matched-text variation in speech delivery rather than from lexical rewriting or broader style transfer. We study this question by holding transcript content fixed and varying six speech-delivery presets whose acoustic attributes may co-vary. We present PJ-Break, a black-box evaluation protocol with presets targeting arousal, authority, and speaking rate, together with AdvAudio-Prosody, a 600-sample benchmark with acoustically verified attributes. On the exact post-QC Qwen2-Audio panel, the Q=1 Panic (38/95), Anger (35/95), and Fast (32/95) presets are all well above Neutral (4/95). The fixed six-query pool covers 44/95 Qwen2-Audio seeds and 15/95 GPT-4o seeds and exceeds a matched-budget StyleBreak reimplementation (27/95) on Qwen2-Audio. A same-voice pool excluding the confounded Commanding condition still reaches 40/95, and a retained-panel ablation shows emotional-delivery audio alone (44/95) is far more effective than emotional text alone (11/95). Exploratory surrogate diagnostics and pilot mitigation observations are secondary, non-core analyses. Overall, matched-text speech delivery should be treated as a first-class factor in Audio LLM safety evaluation

Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential to perpetuate social biases and reinforce stereotypes. In this study, we investigate gender bias in LLMs through the lens of their associations with musical instruments. Building on social-science research on the cultural gender-typing of instruments, we introduce Symphony-Bias, a parallel multimodal dataset spanning text, vision, and audio. We evaluate ten multimodal models with diverse architectures and scales across 22 musical instruments, analyzing how they associate each instrument with three gender categories: {male, female, non-binary}, across three modalities: {text, vision, audio}. Our results show that 92% of instrument-level outcomes align with prior social-science findings, with the harp and drums showing particularly consistent gendered associations across all evaluated models and modalities. We further find that alignment with social stereotypes is weakest in audio, stronger in vision, and strongest in text, suggesting that modality-specific representations can differentially amplify gendered associations with musical instruments.\footnote{The Symphony-Bias dataset will be publicly released upon acceptance of the paper.}

Open Sound Control (OSC) is the dominant wire protocol for real-time parametric control in professional audio, live performance, and virtual production. Large language models can emit plausible OSC, but they hallucinate addresses, mishandle type tags, and fail under paraphrase- unacceptable in show-critical contexts. We present LLM4OSC, a local-first architecture in which models propose structured intent JSON over a human-reviewed device profile, and deterministic code validates, clamps, and encodes before any UDP send. We introduce a frozen evaluation harness with CI gates on wrong-send rate: mismatches that would still pass validation and transmit. On a Max/MSP hero profile (12 patterns; 8 literal + 8 paraphrase + 4 refusal cases), after profile tag enrichment, symbolic slot fill, NL refine, and a retrieval confidence gate, backends B0--B3 all pass frozen gates (100% semantic accuracy, 0% wrong-send). B0 (rules) remains the production default at ~0.05ms; LLM backends remain ~3-4s. Historical few-shot B2 accuracy of 62.5% rises to 100% on this suite only after symbolic post-processing- not because the 0.5B model alone becomes show-safe. We argue for propose-validate-send and wrong-send rate as first-class metrics for language-to-control systems.

Large audio-language models (LALMs) convey acoustic evidence to language decoders through native audio tokens, yet the internal roles of these tokens remain poorly understood. Using temporal audio grounding as a diagnostic setting, we examine how language-model fine-tuning affects the layerwise semantics, decoder accessibility, and temporal output alignment of native audio-token states through four complementary analyses: query-conditioned token semantics, calibrated token readout, temporal-window probes, and residual-delta erasure during generation. Alongside substantial improvements in temporal localization, semantic analysis of Qwen2.5-Omni shows that latent evidence for queried events is already present before fine-tuning and that the audio tokens most strongly aligned with the queried event appear at similar temporal positions before and after fine-tuning. After fine-tuning, event-related information in audio tokens becomes more accessible to the decoder, especially in early and middle layers, and a cross-checkpoint control shows that this improvement arises primarily from decoder adaptation. Temporal probes show that the base checkpoint already contains recoverable information about annotated windows and that fine-tuning mainly improves alignment with each checkpoint's own predicted temporal support. Residual-delta erasure further shows that removing audio-token updates within predicted windows harms timestamp generation more than removing the same number of randomly selected updates. The same broad improvements in decoder readability and prediction alignment also appear in Qwen2-Audio. Together, these results support a semantics-to-readout account in which grounding fine-tuning helps the decoder read existing event evidence and connect it more reliably to temporal outputs.

While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X$^3$-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training, the student generates reasoning trajectories conditioned on its own acoustic perception, while the teacher provides token-level guidance using matched textual inputs and verified answers. We further construct a three-tier symmetric corpus covering textual reasoning rendered into speech, audio-event reasoning grounded in complex acoustic scenes, and spoken-dialogue reasoning involving paralinguistic cues. This design extends cross-modal distillation beyond textually recoverable content to reasoning grounded in non-linguistic events, prosody, and conversational context. Experiments on MMSU, MMAU, BIG Bench Audio, and MMAR demonstrate that X$^3$-OPD substantially improves audio-grounded reasoning and chain-of-thought quality while largely preserving the model's existing capabilities under domain shift.

As large audio language models (LALMs) advance, robust evaluation frameworks have become essential. In this context, Spanish speech understanding under realistic acoustic conditions has received particularly little attention. We introduce ESCUCHA, the first Spanish speech understanding benchmark designed to evaluate LALMs across heterogeneous acoustic conditions and reasoning abilities. ESCUCHA comprises 1,000 human-curated questions paired with audio, totaling 162.9 hours sourced directly ``from the wild'' rather than drawn from existing datasets, with durations ranging from a few seconds to over 80 minutes. The benchmark emphasizes reasoning, spanning 9 perceptual and 10 reasoning categories, and it captures linguistic diversity through multiple Spanish accents and non-normative speech. ESCUCHA further includes multi-audio questions, spoken questions, and audio instructions, and it flags which questions support open-ended evaluation. Benchmarking several state-of-the-art multimodal and speech models reveals substantial performance gaps relative to trained humans.

We present Audio-Visual Flamingo (AV-Flamingo), a fully open state-of-the-art audio-visual large language model (AV-LLM) for joint understanding and reasoning over audio, images, and long-form videos. Unlike prior AV-LLMs that primarily focus on short clips, AV-Flamingo is designed for understanding and reasoning over long and complex real-world (audio-visual) videos. To support this, we make three key contributions: (i) Audio-Visual-Skills, a large-scale collection of real-world videos with ~7M caption and question-answer training instances designed to emphasize temporal, compositional, and cross-modal audio-visual reasoning; (ii) a novel three-stage curriculum that progressively trains the model from short-range perception to long-horizon multi-event reasoning; and (iii) Temporal Audio-Visual Interleaved Chain-of-Thought, a reasoning framework that explicitly grounds intermediate reasoning steps to timestamps in long audio-visual streams, improving temporal alignment and interpretability. Extensive experiments across 15+ audio-visual, omni-modal, audio, and vision benchmarks show that AV-Flamingo outperforms similarly sized open models by clear margins and remains highly competitive with, and in some cases surpasses, much larger open-weight and closed models, particularly on long and complex real-world audio-visual understanding and reasoning tasks. Beyond benchmark performance, AV-Flamingo exhibits strong real-world utility and transfers well to unseen tasks, highlighting its robustness and generalization ability.

Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker verification (ASV). Existing defenses mainly address this threat through binary countermeasures (CMs) for deepfake detection or spoofing-aware speaker verification (SASV), where current systems are dominated by modular ASV-CM fusion and cascaded pipelines. Although large audio language models (LALMs) have shown promise on related audio tasks, including CM and ASV, their use for SASV remains unexplored, despite their capacity to produce natural-language rationales for auditing and robustness beyond discriminative predictions. This work systematically evaluates LALMs for SASV against conventional pipelines under zero-shot prompting, supervised adaptation, reasoning-oriented training, and reinforcement-learning-based optimization. Our results show that pretrained LALMs are near chance in the zero-shot setting, confirming that they are not natively suited to SASV, but that task-specific adaptation closes this gap. We further find that competitive SASV performance can be achieved through several distinct routes. These findings position LALMs as a promising and auditable foundation for unified SASV, while clarifying where conventional cascade systems still lead.

Large audio-language models (LALMs) are increasingly used as automatic judges for speech evaluation. However, high agreement with human ratings does not guarantee that their verdicts are grounded in the audio. A judge may instead rely on specialist labels or reference data supplied by the evaluation protocol itself, taking a shortcut in place of listening to the audio. In this paper, we audit such protocol-level ``shortcuts'' in LALM judges across three common deployment protocols: feature-blueprint judging, where the audio is replaced by a structured text description of acoustic features, reference-conditioned judging, and pairwise A/B comparison. Across six judges and four attributes, we find that several LALMs rely on protocol-level shortcuts. For example, in feature-blueprint judging, incorrect specialist labels reduce five judges' emotion accuracy to 0.10 or below, and in concatenated A/B comparisons, Qwen3-Omni-Thinking often picks the same slot regardless of order swaps. These results indicate that aggregate agreement can overstate the validity of LALM judges unless the model and the evaluation protocol are assessed jointly, and that each model-protocol pair should be evaluated with a matched shortcut probe.

Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order. This gap arises because existing evaluation and training signals mainly emphasize global similarity or perceptual quality, with limited supervision on instruction-level correctness. We propose an instruction-level framework that uses audio-aware large language models (ALLMs) as fine-grained judges to verify target event presence and temporal relations in generated audio. After validating ALLM judgments on benchmarks and through human verification, we use their feedback to construct preference pairs for direct preference optimization. We further introduce S3Bench, a narrative benchmark for evaluating multi-event temporal instruction following. Experiments show that our method improves event completeness, temporal ordering, and joint instruction-following accuracy across existing benchmarks and S3Bench, while maintaining audio quality.

Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content. Improving this without the cost of retraining calls for an effective inference-time intervention, yet most existing methods intervene only after the audio encoder and operate at a relatively coarse granularity. The encoder itself, where acoustic information is first extracted from the waveform, remains largely unexplored, especially at the level of individual neurons. We introduce IAAN, Identifying and Amplifying Acoustic Neurons, a training-free and label-free method that scores each feed-forward neuron in the audio encoder by contrasting its activation on the real waveform with that on a noise reference lacking the real audio's acoustic information. IAAN then amplifies a small set of the highest-scoring neurons at inference. Across ten non-semantic speech attributes, IAAN improves average accuracy by 25.7 points on Audio-Flamingo-3, 21.4 on Qwen2.5-Omni, and 9.7 on Kimi-Audio. It also improves a model already explicitly fine-tuned to prioritize acoustic evidence. In controlled comparisons, both the encoder locus and neuron-level selectivity prove necessary for this gain. Intervening after the encoder, at the decoding side or inside the language model, yields little to no improvement, or even deteriorates accuracy. The improvement also depends on which specific neurons are amplified, not merely on their number, confirming that IAAN's acoustic score succeeds in identifying the neurons that matter. These results show that a small, precisely targeted intervention inside the audio encoder is an effective and largely untapped way to strengthen the acoustic understanding of LALMs, opening a new direction for inference-time methods that improve acoustic perception through neuron-level access to the encoder.

Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input. Our approach interleaves periodic time markers with continuous audio tokens using large-scale synthetic supervision from a cascaded pipeline. Our model achieves strong temporal-grounding accuracy on short and long benchmarks and supports time-anchored fragment descriptions and summaries. Extensive ablations examine how time representation, marker frequency, tokenization, and duration-mixture design affect accuracy and computational cost. We release model weights and datasets to support further research on time-aware audio understanding, available at https://huggingface.co/ai-sage/GigaChat3.1-Audio-10B-A1.8B.

Multimodal Large Language Models (LLMs) have remarkable semantic audio understanding, yet they remain "spatially agnostic" due to their reliance on mono-channel audio representations. Currently, spatial audio perception methods mainly focus on complex room simulations and custom-trained, geometry-aware stereo encoders, which limits their accessibility and generalizability. In this paper, we introduce the Dual-BEATs architecture, in which the left and right audio channels are routed independently through two identical semantic encoders as an alternative to specialized spatial modules. To circumvent the architectural bottleneck where internal normalization otherwise erases the inter-channel variance of stereo audio, we inject a static, uncorrelated dithering noise floor prior to encoding. This dithering intervention establishes a macro-variance floor that "smuggles" spatial geometry across the normalization layers. Evaluated on a ternary directional classification task (Left, Center, Right), we demonstrate that dithered models achieve exceptional spatial resolution--reaching up to 97.2% localization accuracy even on subtle 0.5 panning amplitudes--and demonstrates robust, zero-shot generalization to entirely unseen spatial configurations. Our results suggest that with the appropriate acoustic regularization, standard multimodal models are natively capable of generalized stereo audio understanding.

Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set. At the intersection of these paradigms lies the task of Open-Vocabulary Audio Event Grounding: predicting all time intervals of a target sound event described by an arbitrary natural language query. While this task is crucial for real-world audio understanding and LALM adaptation, it is bottlenecked by data scarcity. Few large-scale resources provide open-vocabulary onset/offset supervision, and manual temporal annotation is prohibitively expensive. To address this, we introduce Auto-AEG, a scalable pipeline that constructs such supervision by automatic data construction and model fine-tuning. It pairs programmatically synthesized clips, which carry exact ground-truth intervals for supervised cold-start, with multi-model pseudo-labels on real-world audio that supply the reward signal for reinforcement learning. Training with this pipeline yields promising performance gains on both the DESED SED benchmark and AEGBench, an independent difficulty-stratified benchmark we release. Our results show that automatically constructed data, coupled with interval-aware reward function design, is an effective data-side route to expanding the temporal localization capability of LALMs.

Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors. While contrastive decoding (CD) offers training-free mitigation, existing methods rely on blunt perturbations like masking or noise, leaving structured audio transformations unexplored. We explore this design space by evaluating a diverse library of targeted audio perturbations and adaptively selecting the optimal negative branch for each task and example. First, we improve upon earlier prompt engineering by showing that a simple binary yes/no constraint reduces the model's tendency to falsely confirm absent audio features. Second, evaluating our library across temporal, spectral, frequency, and amplitude domains reveals that optimal transformations are highly task-dependent; for instance, reversing the audio array disrupts temporal coherence, raising accuracy on the temporal order task from 74.7% to 81.4%. Finally, we trained a light-weight perturbation selector on model hidden states to dynamically route negative branches, yielding an additional +4.3% gain on the existence task.

Audio-Language Models (ALMs) achieve strong zero-shot performance by aligning audio with textual class descriptions. Although prompt learning improves accuracy on base classes through few-shot supervised adaptation, we observe a critical trade-off: it often degrades performance on novel classes, sometimes falling below zero-shot accuracy. This exposes a base-to-novel generalization gap in prompt learning for ALMs. To address this issue, we propose \textbf{ZEBRA} (Zero-shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization), a plug-and-play framework that fuses zero-shot logits with prompt-learning logits, and employs self-entropy regularization to reduce overfitting to base classes. Experiments across multiple audio classification datasets show that ZEBRA consistently improves novel-class performance while maintaining strong base accuracy, significantly reducing the base-to-novel gap compared to standard prompt learning. The code is available at: https://github.com/asif-hanif/zebra.

Recent music audio-language models achieve high accuracy on instrument question-answering benchmarks, but it remains unclear whether this reflects robust audio grounding or benchmark-specific shortcuts. In this paper, we introduce an OpenMIC-derived diagnostic benchmark sequence for instrument grounding in music audio-language models, extending binary instrument-presence QA to genre-prior-reduced examples, confusable instrument discrimination, longer audio context, and temporal localization. Across these settings, high binary QA accuracy often fails to predict model behavior: models can exhibit option-position bias, confusable-instrument errors, and temporal response bias. These results suggest that instrument grounding should be evaluated with multi-axis diagnostic benchmarks rather than a single aggregate accuracy.

Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external APIs, including adaptation to platform-specific data distributions, policy-specific objectives, and product-level safety constraints. As a result, platforms must undertake internal model development, naturally turning to shared public research for guidance. However, existing multimodal foundation-model studies primarily report architectures, training recipes, data scaling strategies, and benchmark results, but provide less systematic guidance on how failures should be localized and translated into targeted model-development interventions. Interventions are essential because deployment failures are rarely self-explanatory. Similar failures can originate from different causes. Without targeted interventions, improvement reduces to heuristic trial-and-error, where benchmark improvements are weakly attributable, and failures are difficult to trace to their underlying causes. To address this gap, we present a diagnostic methodology for industry-scale Audio-Visual-Language Models AVLM development. The methodology maps model failures into a taxonomy of observable failure signatures and links each class of failure to an intervention space. We instantiate this methodology across the development and alignment lifecycle of an AVLM foundation model for a large-scale video and live-streaming platform. The resulting system supports over 100 regions and is designed for noisy, ambiguous, and highly diverse content drawn from global platform traffic.

Audio-Visual Speech Recognition takes two input modalities, acoustic and visual streams, where visual information from lip movements aids recognition when audio is noisy. Recently, LLM-based AVSR models have emerged as a promising paradigm by connecting pre-trained audio-visual encoders to an LLM, achieving strong results in clean conditions. However, these models are predominantly optimized for clean acoustic conditions, with limited attention to making the LLM backbone robust to noise. No explicit mechanism is employed to produce stable representations under corrupted audio, leading to performance degradation in noisy environments. To address this, we propose VIB-AVSR, which integrates Variational Information Bottleneck layers at targeted positions within the LLM backbone to regularize representations. VIB-AVSR reduces degradation under noisy conditions across multiple SNR levels and noise types, without requiring architectural modifications or additional training data.

Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space. While effective, existing retrieval embeddings are primarily optimized for audio--caption matching, limiting their ability to support diverse retrieval objectives and controllable retrieval behaviors. We present ALM2Vec, a universal audio embedding framework derived from pretrained large audio--language models (LALMs). By transferring the audio understanding, instruction-following, and reasoning capabilities acquired through large-scale multimodal training, ALM2Vec learns a unified embedding space for retrieval across audio domains and task types. Beyond conventional text--audio retrieval, ALM2Vec incorporates natural-language instructions into the embedding process, enabling instruction-aware retrieval for scenarios such as audio question answering and aspect-conditioned retrieval. Experimental results show that ALM2Vec achieves competitive performance on standard audio and speech retrieval benchmarks while exhibiting promising compositional and controllable retrieval capabilities, highlighting its potential as a unified audio embedding model for retrieval across domains, tasks, and user intents.

Recent Large Audio Language Models (LALMs) have achieved remarkable progress in audio perceptual tasks across individual acoustic layers, including speech, sound, and music. However, existing benchmarks predominantly evaluate these layers in isolation, overlooking the complex contextual relationships that arise when multiple acoustic sources co-occur in real-world auditory scenes. Real-world auditory interpretation requires Context-Aware Auditory Scene Understanding (CASU): the ability to comprehend the holistic scene by integrating sound layers. To evaluate this capability, we introduce the CASU benchmark, which assesses whether Audio LLMs can interpret auditory scenes composed of speech, acoustic events (e.g., announcements), and background environments (e.g., traffic), and reason about the logical relationships between these layers. We propose a scalable pipeline for constructing time-accurate, semi-synthetic audio streams by composing real-world scene sounds with synthetic speech. Building on this data, we design four tasks that probe scene understanding: contextual question answering, entity extraction from the scene, speaker role inference, and counterfactual reasoning where scene is manipulated. Experiments across multiple LALMs demonstrate that effective auditory scene understanding requires integration over all auditory layers, rather than reliance on speech or sound alone, underscoring the necessity of CASU for advancing complex audio understanding in LALMs.

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.

Large audio-language models (LALMs) can reason about audio, yet it remains unclear whether they can perform comparative judgments between two speech signals along emotional, environmental, linguistic, prosodic, and interpersonal dimensions. We study this question in the context of speech emotion recognition (SER), where the model determines which utterance exhibits higher arousal, valence, or dominance. We introduce a reasoning-guided ordinal SER framework that conditions an LALM on paired speech inputs. The model is trained using reasoning traces generated from both semantic audio descriptions and acoustic evidence derived from GeMAPS features, enabling interpretable comparative decisions. Beyond direct supervision, we also employ direct preference optimization to encourage stronger separation for emotional differences. Experiments show that the proposed framework improves preference prediction while requiring only 5% of the training data used by conventional ordinal SER systems.

Large automatic speech recognition (ASR) models such as Whisper must be deployed across hardware with widely varying memory and inference-speed constraints. We present a compression framework that jointly parametrizes Whisper deployment along \emph{six} dimensions: model size, temporal resolution, encoder token stride, low-rank adaptation capacity, weight precision and sparsity pattern. All axes are jointly optimized using NSGA-III with respect to three deployment objectives: word error rate (WER), inference FLOPs, and memory footprint. Across 50 of the 1,680 candidate configurations evaluated, we characterize the conditional effect of each axis and identify compression combinations that dominate naive single-axis scaling, while finding that 1:4 structured sparsity fails to recover acceptable accuracy under the tested recovery budgets. We report measured WER and resident memory, use analytical EffFLOPs as the search-time compute surrogate, and separately validate representative inference configurations using measured real-time factor (RTF).

We frame the system as diagnostic data curation for a large audio-language model: before fine-tuning, we probe Qwen3-Omni-30B-A3B-Instruct under normal, empty-audio, and shuffled-audio conditions to identify how the model's answers change when audio evidence is removed or mismatched. These model confusion patterns are used to bucket training samples into text-prior, shuffle-leak, strong audio-dependent, and hard or misleading cases. Our strongest train-only system fine-tunes only on strong-audio items, where the normal audio-question pair is correct but both counterfactual variants fail, plus a small number of empty-audio negatives and a text-only response normalizer for parse-failed generations. On the official development set, the best train-only system reaches 67.27% accuracy after response normalization, compared with 65.90% for our local Qwen3-Omni baseline. Final submissions additionally include models trained using train+development splits and a three-model ensemble.

Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio tasks. As they are increasingly deployed in real-world applications, ensuring their safety alignment has become more important. Although refusal mechanisms serve as a key safeguard by preventing LALMs from responding to harmful requests, they can also lead to {\em over-refusal}, where models incorrectly reject benign queries. This issue is especially challenging in the audio domain because speech that appears harmful in isolation may become benign when interpreted together with the surrounding acoustic context, such as background sounds. To study this problem, we introduce \textbf{AOR-Bench} (\textbf{A}udio \textbf{O}ver-\textbf{R}efusal \textbf{Bench}mark), the first benchmark for over-refusal specifically designed for LALMs. AOR-Bench contains 3,000 pseudo-harmful audio samples across six scenario categories. Evaluating 12 representative LALMs from six major model families, we find that over-refusal is widespread (Figure~\ref{fig:overall_performance}) and uncover several important patterns in their safety judgments. As a preliminary effort to mitigate this issue, we further explore two lightweight strategies (e.g., Chain-of-Thought and activation steering) to reduce over-refusal.

Acoustic environments often contain multiple overlapping sound events, and the same acoustic scene can be described using diverse textual expressions, making audio-text alignment inherently ambiguous. This paper proposes a probabilistic audio-language pretraining framework to model many-to-many correspondence ambiguity in audio-text alignment. Unlike conventional contrastive methods that learn deterministic point embeddings, our approach represents each modality as a distribution and learns uncertainty-aware cross-modal alignment. Rather than relying on masking-based uncertainty simulation, we mix audio-text pairs to create overlapping sounds that better reflect real acoustic mixtures and capture semantic inclusion relations among sound events. We further introduce a multi-level inclusion loss to enforce representations consistent with these relations. Experiments on audio-text retrieval benchmarks show that the proposed method outperforms deterministic baselines.

AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear whether these models genuinely utilise such context or rely on parametric knowledge learned during pretraining. Existing benchmarks cannot answer this question because they evaluate transcription under fixed prompting conditions and rarely include explicit contextual inputs. We introduce IndicContextEval, a 56-hour multilingual benchmark of natural speech from 555 speakers across 8 Indian languages and 23 professional domains. We design a 7-level prompting framework that progressively introduces contextual signals, including metadata, natural-language descriptions, entity lists in English and native script, and adversarial prompts with incorrect entities. Evaluating five models reveals substantial differences in context utilisation behaviour, highlighting the need for explicit evaluation of contextual grounding in AudioLLMs.

While Audio Large Language Models (Audio LLMs) excel at multimodal understanding, they suffer from text dominance, a bias where models blindly favor text over acoustic evidence, causing hallucinations. However, the internal mechanisms underlying how these models behave when audio and textual inputs contradict each other remain unexplored. In this work, we present the first mechanistic analysis of this phenomenon by tracing the propagation of internal representations across layers. Our investigation reveals three key findings: (i) text dominance is systematically and empirically across models; (ii) while text and audio rely on functionally distinct pathways, they ultimately converge into a shared semantic space in late layers; and (iii) the text pathway does not erase audio information, but rather actively suppresses intact audio representations. Building on these insights, we leverage back-patching, a training-free intervention that routes late-layer audio activations back into earlier layers. This amplifies the audio representations, enabling them to overcome textual suppression. Our evaluation shows that back-patching consistently reduces text dominance, paving the way for mechanistic multimodal alignment under conflict.

Large Audio Language Models (LALMs) achieve strong performance on a variety of audio understanding tasks but continue to struggle with temporal reasoning, a fundamental capability central to human auditory perception. Understanding the causes of these failures remains challenging as existing benchmarks report performance gaps without probing underlying mechanisms. To address this, we introduce a benchmark with 1,657 questions across three foundational tasks designed specifically for mechanistic analysis. Examining model outputs across varying input settings (behavioral analysis) reveals that models often under-utilize audio when textual cues are available. We also provide the first causal mechanistic analysis of temporal reasoning failures in LALMs. Comparing attention upweighting against scaling, we find that redistributing attention across audio tokens is more effective than increasing audio attention. Targeting task-relevant tokens yields further gains. These findings suggest that modality imbalance alone cannot explain failures. Attention scaling at bottleneck layers improves accuracy from 55.9% to 59.1% without fine-tuning, demonstrating a promising direction for future work.

Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail. We benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78, 0.81] and collapse by about -0.20 F1 at horizon h=200. We introduce NarrativeWorldBench, an open benchmark of nine narrative-structure metrics evaluated across horizons h in {10, 20, 50, 100, 200}, with cross-lingual evaluation across four Indic languages (Hindi, Tamil, Telugu, Marathi). We introduce N-VSSM, a Narrative Variational State-Space Model that maintains a structured 256-dimensional latent world state over more than 200 episodes via a Mamba-2 backbone with an event-conditioned posterior and an 8B decoder. N-VSSM holds plot-beat F1 >= 0.84 across all horizons at 4x lower compute than the closed-frontier band. A learned Cultural Transfer Function lifts cross-language fidelity by +0.20 to +0.23 Likert points. In a within-subjects writer study (n = 12 professional authors, 240 trials), N-VSSM is preferred over Claude Opus 4.5 on long-arc consistency 71% of the time and rated +1.3 Likert points higher on controllability.

Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning. A practical way to improve such capabilities is post-training, whose effectiveness critically depends on the quality and diversity of training data. However, existing audio-language datasets often contain substantial redundancy, where many samples are highly similar in acoustic content and thus provide overlapping supervisory signals. Such redundancy not only increases annotation cost, but also limits corpus diversity and reduces the effectiveness of post-training. To address this issue, we propose a redundancy-aware data construction pipeline for building reasoning-oriented supervision for LALMs. Specifically, we first perform acoustic similarity-based deduplication across raw audio datasets to improve corpus diversity. We then integrate existing audio captions and question-answer pairs into a unified multiple-choice format. Based on these unified annotations, we leverage Qwen3-30B to generate chain-of-thought (CoT) rationales for reasoning-oriented supervision. Based on this pipeline, we construct AudioDER, a reasoning-oriented post-training dataset containing approximately 191k samples spanning sound, speech, and music. Each sample consists of an audio clip, a multiple-choice question, four answer candidates, an audio caption, and a CoT rationale. Extensive experiments show that post-training on AudioDER consistently improves the performance of Qwen2-Audio-7B-Instruct on multiple audio reasoning benchmarks, including MMAU-mini, MMSU, and MMAR. We hope AudioDER can serve as a valuable resource for advancing audio reasoning research and the development of more capable LALMs.

Sound events are entities with semantic identities, locations, and trajectories, but current audio-language models usually reason about clips as global event content. Conversely, sound event localization models track source directions over time but offer limited semantic coverage for language reasoning. To address this gap, we introduce ST-AudioQA, a spatio-temporal audio QA dataset and benchmark built from first-order ambisonic (FOA) renderings of static and moving sound sources. Each scene provides source identity, activity, direction, distance, and motion metadata, enabling dense trajectory supervision and questions about what is sounding, where it is, how it moves, and how sources relate. We further propose ST-Audio Encoder, a time-resolved FOA audio encoder that learns event semantics together with source trajectories, and ST-AudioLM, which connects the audio tokens from the encoder to an LLM for spatio-temporal audio QA. Experiments show that this representation improves the semantic-localization tradeoff and yields stronger reasoning performance than static spatial and localization-oriented baselines.

A crucial aspect of linguistic capability is the ability to trade off between stored representations and abstract knowledge: one must retrieve learned representations, but also generate novel ones by applying productive rules. While recent work has examined abstract knowledge in language models, holistic storage of multi-word units has received far less attention. We probe internal representations in text-based LLMs and an ASR model, testing whether V+up phrasal verbs develop distinct representations as a function of frequency and predictability. All models show evidence of holistic storage driven by frequency and predictability, further supporting usage-based theories of language.

Large-scale mined corpora provide abundant training data for end-to-end speech-to-speech translation (S2ST) but may contain noise, misalignment, and semantic errors. Filtering noisy data is crucial to maintain robust speech translation performance. We study how to train an audio-language model to make keep/drop decisions on paired speech directly from audio. To obtain reliable supervision without manual labels, we adopt a scalable two-stage Rank-to-Distill strategy. A lightweight ranker generates keep/drop pseudo-labels from noisy speech pairs, then trains an audio large language model to predict keep/drop directly from raw paired speech. The resulting model jointly captures acoustic fidelity and cross-lingual semantic consistency for the selection of speech-conditioned data. Experiments on CVSS-C and SpeechMatrix show consistent improvements over unfiltered training, yielding up to +1.4 ASR-BLEU for end-to-end S2ST.

Spoken dialogue models typically start from text LLM backbones, yet reasoning often degrades when conditioning on speech instead of text. We attribute part of this modality gap to a temporal-granularity mismatch: speech tokens are temporally redundant and far longer than text under matched semantics, diluting per-token semantic density and weakening text-native reasoning dynamics. We study speech token design as a representation selection problem and sweep frame rates under a frozen LLM backbone with a fixed information rate. To make low frame rates feasible, we introduce factorized FSQ and a lightweight non-autoregressive audio LM head, scaling capacity to nearly 300,bits/frame without sacrificing efficient prediction. With the bottleneck removed, we sweep frame rates (50$\rightarrow$2.08,Hz) and alignment depth, and observe a consistent best regime for speech QA at 4.17,Hz with intermediate-layer representation alignment.