arXiv subjects

Zhenhong Zhou

Publications and source records attributed to Zhenhong Zhou.

At least 19 recordsLinked to original sources

arXiv2026

Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models

Audio large language models (ALLMs) can reason about the content of audio recordings to perform complex tasks. However, these capabilities usually collapse in real-world environments when background noise and competing sources mix the target sound. Inspired by long-term memory in human listening, we propose Long-Term Memory-Guided Audio Enhancement (LTM-AE) to improve selective target perception by refining the audio representations of ALLMs without training. LTM-AE extracts representations in hidden states from separate clean reference recordings as long-term memory for each category, guiding enhancement toward a user-specified listening target. We reconstruct incoming audio tokens in the selected category long-term memory and interpolate the reconstructions with the original tokens before language backbone decoding. This interpolation controls the influence of stored auditory experience while keeping all ALLM parameters fixed. Diagnostic readouts across twenty sound categories and three ALLMs show that LTM-AE strengthens responses to a specified target amid three interfering sources. Averaged over constrained and free-form classification, accuracy gains over raw mixtures range from 29.53 to 46.15 percentage points across multiple open source models. For speech content recovery, LTM-AE with an additional learned token-level gate reduces Qwen2-Audio's word error rate from 23.07% to 14.77%. This work takes an initial step toward using principles of human long-term memory to enhance ALLMs for real-world listening. Our code is available at https://github.com/aynlp/ltm-audio-code

cs.SD↗

arXiv2026

RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning

Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. However, existing circuit studies emphasize preserving functionality or explaining safety, leaving the mechanisms underlying failures across a broader range of tasks largely unexplored. Extending circuit analysis from abilities to errors, we explore the perspective that such failures may likewise arise from erroneous internal computations and that targeted tuning of the corresponding parameters can correct such errors while largely preserving other capabilities. Motivated by this insight, we introduce RESCUE (Reasoning-Error Sparse-Circuit Uncovering and Editing), a framework that localizes error-associated circuits and surgically repairs them for performance enhancement. General tasks typically involve multi-step reasoning and long-form generation, where early deviations can cause prefixes to drift from supervised references, leading SFT-based mask optimization to overlook circuits involved in generation-time errors. RESCUE therefore refines these masks through reinforcement learning with multiple masked-model rollouts, improving their relevance to observed task failures. Finally, RESCUE introduces a pruning technique and precisely fine-tunes error circuits to correct task failures, thereby translating error localization into a sparse and targeted model update. We validate RESCUE on heterogeneous repair sets across two domains: (1) mathematical reasoning, identifying a math error circuit of 1.40% density whose repair raises accuracy from 6.0% to 75.5%; and (2) medical QA, where a similarly compact 1.44% circuit improves repair-set accuracy from 0% to 81%. Our code is available at: https://github.com/chuanpupig/RESCUE.

cs.LG↗

arXiv2026

Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models

Visual token compression reduces the inference cost of Large Vision-Language Models (LVLMs). However, aggregate robustness measures do not reveal whether a particular adversarial failure is induced by compression or inherited from the underlying model. We define a compression-specific failure (CSF) as an adversarial input that remains correct under full-token inference but fails after compression, casting compression-induced risk as a paired failure attribution problem. Within a controlled diagnostic cohort, counterfactuals show that retained-set allocation causally changes compressed correctness and reveal a negative association between recovery and representation drift in displaced evidence. Motivated by these findings, we propose CIRA, a Compression-Induced Risk Attack for Large Vision-Language Models. Under a vision-encoder white-box setting, CIRA optimizes image perturbations through encoder-side objectives that manipulate token priorities across candidate compression budgets while preserving displaced evidence. CIRA uses no downstream questions or labels and requires no access to the language model, deployed compressor, or exact compression budget. Across 12 dataset-compressor settings evaluated at four budgets, CIRA achieves a mean CSFR of 20.35% while limiting full-token attack success to 6.92%, with similar behavior on additional LVLM families. A cross-view selection-stabilization defense substantially suppresses CIRA, although Adaptive CIRA partially restores its effectiveness. These results show that compression-specific failures persist under restricted access and support paired evaluation of full-token and compressed inference for attributing risk to visual-token compression.

cs.CV↗

arXiv2026

In-Place Instruction Following in Diffusion Language Models

Diffusion Large Language Models (dLLMs) generate text via bidirectional iterative denoising, naturally supporting user-specified constraints anchored at arbitrary output positions, a paradigm known as In-place Prompting (IPP). We formalize this as the In-place Instruction Following (IIF) task and construct IIF-Bench, a hierarchical benchmark spanning literal, style, and discourse-function constraints, paired with a rubric-based local-global evaluation protocol. An inference-time attention-bias probe suggests that vanilla dLLMs often under-prioritize constraint spans during denoising. We then propose GRAFT, an IPP-oriented post-training framework combining constraint-aware SFT and preference optimization. On four representative dLLMs, GRAFT raises the average IIF score from 57.75 to 73.10 (+15.35 points), with absolute gains of 15.91 and 15.57 points on literal and discourse-function constraints, while preserving general generation ability.

cs.CL↗

arXiv2026

From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs

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.

cs.SD↗

arXiv2026

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook

Advances in Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs). Among these, Large Audio Language Models (LALMs) are essential for realizing universal auditory intelligence. Despite their remarkable performance, the escalation of LALMs' capabilities has significantly outpaced the development of systemic frameworks to ensure their trustworthiness. This survey provides a comprehensive investigation into the endogenous mechanisms of LALMs, detailing the architectural innovations and alignment algorithms that facilitate emergent reasoning. Specifically, we analyze how the transition to unified end-to-end frameworks and the integration of continuous acoustic signals expand the attack surface. To rigorously evaluate the risks within these paradigms, we establish a comprehensive taxonomy of trustworthiness, categorizing critical vulnerabilities such as cross-modal jailbreaking, latent acoustic backdoors, and biometric privacy leakage. We review the state-of-the-art LALMs through six analytical pillars: hallucination, robustness, safety, privacy, fairness, and authentication. The pronounced imbalance between a mature offensive landscape and underdeveloped defenses highlights persistent trustworthiness gaps and multidimensional risks in audio-centric intelligence. Finally, we propose a roadmap advocating for ``Defense-in-Depth'' architectures, causal auditory world modeling, and intrinsic representation engineering to support the development of more reliable and trustworthy audio intelligence. Our project has been uploaded to GitHub https://github.com/Kwwwww74/Awesome-Trustworthy-AudioLLMs.

cs.SD↗

arXiv2026

ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models

Although Audio Large Language Models (ALLMs) have witnessed substantial advancements, their long audio understanding capabilities remain unexplored. A plethora of benchmarks have been proposed for general audio tasks, they predominantly focus on short-form clips, leaving without a consensus on evaluating ALLMs over extended durations. This paper proposes ChronosAudio, the first multi-task benchmark tailored for long-audio understanding in ALLMs. It encompasses six major task categories and comprises 36,000 test instances totaling over 200 hours audio, stratified into short, middle, and long-form categories to comprehensively evaluate length generalization. Extensive experiments on 16 state-of-the-art models using ChronosAudio yield three critical findings: 1.Precipitous Long-Context Collapse: ALLMs exhibit a severe inability to sustain performance, with the transition from short to long contexts triggering a staggering performance degradation of over 90% in specific tasks. 2.Structural Attention Dilution: Performance degradation stems from a fundamental failure in maintaining temporal locality; attention mechanisms suffer from significant diffusion in later sequences. 3.Restorative Ceiling of Mitigation: Current strategies only offer 50% recovery. These findings reveal significant challenges in long-audio, underscoring the urgent need for approaches to achieve robust, document-level audio reasoning.

cs.SD↗

arXiv2026

Structure-Guided Visual Perturbation Neutralization for LVLMs

Image inputs enable Large Vision Language Models (LVLMs) to perceive fine-grained visual information, but also introduce a pixel-level attack surface through which adversarial perturbations can elicit unsafe model behaviors. However, most existing defenses are designed for traditional computer vision settings and thus often overlook the cross-modal alignment required by LVLMs, leading to degraded performance. Meanwhile, the limited defenses tailored to LVLMs often require substantial image modifications and introduce considerable computational overhead, thereby compromising inference quality and efficiency. To address these limitations, we propose Structure-Induced Guided Neutralization (SIGN), a lightweight, plug-and-play defense framework that improves LVLM compatibility via Prior Structural Extraction and achieves efficient perturbation suppression via Dynamic Guided Neutralization. Extensive experiments show that SIGN achieves over 87\% defense success rate with only 0.5\% pixel modification and 0.16 seconds per image, while nearly preserving original visual representations and benign task performance. Our work offers a lightweight alternative to defenses that require costly model training and highlights the potential of exploiting a vision encoder for efficient adversarial protection. Our code is open source on https://anonymous.4open.science/r/SIGN-BCB1.

cs.CV↗

arXiv2026

Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose \ourmethod, a defense framework that requires no prior knowledge of trigger settings. \ourmethod is based on the key observation that when deliberately injecting known backdoors into an already-compromised model, both existing unknown and newly injected backdoors aggregate in the representation space. \ourmethod leverages this through a two-stage process: \textbf{first}, aggregating backdoor representations by injecting known triggers, and \textbf{then}, performing recovery fine-tuning to restore benign outputs. Extensive experiments across multiple LLM architectures demonstrate that: (I) \ourmethod reduces the average Attack Success Rate to 4.41\% across multiple benchmarks, outperforming existing baselines by 28.1\%$\sim$69.3\%$\uparrow$. (II) Clean accuracy and utility are preserved within 0.5\% of the original model, ensuring negligible impact on legitimate tasks. (III) The defense generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.

cs.CL↗

arXiv2026

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion

In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tension between competing goals dictates that aggressively optimizing for one metric (e.g., helpfulness) frequently incurs a substantial penalty on another (e.g., harmlessness). While prior work mainly focuses on data selection, parameter merging, or algorithmic balancing during training, these approaches merely force compromises between divergent preferences along a fixed Pareto frontier, failing to fundamentally resolve the inherent trade-off. In this work, we approach this problem from a novel perspective of multi-dimensional rewards. By scaling up the model's rollouts and analyzing the outputs across different reward dimensions, we arrive at a critical conclusion: the conflict among multiple objectives stems from the fact that the prompt itself inherently restricts the achievable multi-dimensional rewards. Based on this core observation, we propose MORA: Multi-Objective Reward Assimilation. Specifically, MORA isolates single-reward prompts through pre-sampling and expands their reward diversity by rewriting the original questions to incorporate multi-dimensional intents. Extensive experiments demonstrate that: (1) in sequential alignment, MORA achieves single-preference improvements ranging from 5% to 12.4%, with exceptional gains in harmlessness, after multiple-preference alignment across helpful, harmless, and truthful dimensions. (2) In simultaneous alignment, MORA achieves an average overall reward improvement of 4.6%. Our codes are available at https://github.com/Shiying-Huang/MORA-MPA.

cs.AI↗

arXiv2026

EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs

Audio Large Language Models (ALLMs) are highly vulnerable to real-world noise, which often induces severe semantic drift and hallucinations. Existing robustness methods primarily rely on waveform-level acoustic enhancement, answer-level supervision, or the internal suppression of noise representations. To address these issues, we propose echodistill, an alignment-based noisy-to-clean self-distillation framework. Echodistill leverages a frozen clean-audio teacher to provide semantic references for an inference-time noisy-audio student. Specifically, the student samples candidate responses under noisy conditions to expose its test-time behavior. These trajectories are then optimized via group-relative policy optimization (GRPO), where the token-level consistency with the teacher acts as a reward bonus. By aligning the noisy student's candidate responses with clean semantic evidence, and applying audio-aware reward shaping, our method encourages reasoning trajectories that are both correct and genuinely acoustically grounded. Echodistill significantly improves the semantic reliability and task performance of Audio LLMs under complex noise, without introducing any additional inference costs. Extensive experiments show that: (I) Compared with the strongest baseline, echodistill achieves average improvements of 4.18\%$\uparrow$ in GSR under strong noise. (II) Ablation results on Qwen-Omni further show that echodistill improves over the GRPO-only variant by 3.02\%$\uparrow$ in Acc, 3.89\%$\uparrow$ in Noisy, and 4.53\%$\uparrow$ in GSR on average. Our codes are available at https://anonymous.4open.science/r/echodistill-10DE.

cs.CL↗

arXiv2026

RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios

While Audio Large Models (ALMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics -- or ``Acoustic Ecology'' -- that characterize authentic physical environments. To bridge this ecological gap, we introduce \textbf{RSA-Bench}, a comprehensive robustness benchmark designed to stress-test ALLMs through high-fidelity auditory scene simulations. Unlike traditional methods, we construct evaluation samples by naturally superimposing diverse environmental soundscapes -- spanning \textit{Pasture}, \textit{Extreme Weather}, \textit{Classroom}, and \textit{Outdoors} -- onto clean speech signals across a spectrum of interference intensities. By evaluating models on six core tasks ranging from fundamental perception to complex reasoning, our study unveils three macro-level insights: \textbf{(I) The Perception-Cognition Gap:} Models maintain relative resilience in low-level recognition but suffer a \textbf{functional collapse} in high-order reasoning tasks under stress; \textbf{(II) Scenario Sensitivity:} ``Vocal-like'' interference (e.g., background laughter) proves significantly more destructive than mechanical noise, challenging the model's auditory attention mechanisms; and \textbf{(III) The Denoising Paradox:} Standard speech enhancement often exacerbates performance degradation, as ALLMs prove highly sensitive to the semantic distortions introduced by denoising artifacts.

cs.SD↗

arXiv2026

Resource Consumption Threats in Large Language Models

Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LLMs increase service capacity for providers and reduce latency and API costs for users. Recent resource consumption threats induce excessive generation, degrading model efficiency and harming both service availability and economic sustainability. This survey presents a systematic review of threats to resource consumption in LLMs. We further establish a unified view of this emerging area by clarifying its scope and examining the problem along the full pipeline from threat induction to mechanism understanding and mitigation. Our goal is to clarify the problem landscape for this emerging area, thereby providing a clearer foundation for characterization and mitigation.

cs.CR↗

arXiv2026

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from Autoregressive LLMs, stemming from their iterative and parallel generation mechanisms. In this paper, we conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics. Experimental results reveal a harmful bias inherent in the standard greedy remasking strategy and identify a critical phenomenon we term Denoising-path Dependence, where the safety of early-stage tokens decisively influences the final output. These findings also indicate that while current decoding strategies constitute a significant vulnerability, dLLMs possess a substantial intrinsic safety potential. To unlock this potential, we propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach: Stochastic Annealing Remasking dynamically introduces controlled randomness to mitigate greedy selection bias, while Block-level Audit and Repair exploits internal model representations for autonomous risk detection and guided correction. Comprehensive experiments on four dLLMs demonstrate DiffuGuard's exceptional effectiveness, reducing Attack Success Rate against six diverse jailbreak methods from 47.9% to 14.7% while preserving model utility and efficiency. Our code is available at: https://github.com/niez233/DiffuGuard.

cs.CL↗

arXiv2026

SafeSeek: Universal Attribution of Safety Circuits in Language Models

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods struggle with generalization and reliability due to their reliance on heuristic, domain-specific metrics and search algorithms. To address this, we propose \ourmethod, a unified safety interpretability framework that identifies functionally complete safety circuits in LLMs via optimization. Unlike methods focusing on isolated heads or neurons, \ourmethod introduces differentiable binary masks to extract multi-granular circuits through gradient descent on safety datasets, while integrates Safety Circuit Tuning to utilize these sparse circuits for efficient safety fine-tuning. We validate \ourmethod in two key scenarios in LLM safety: \textbf{(1) backdoor attacks}, identifying a backdoor circuit with 0.42\% sparsity, whose ablation eradicates the Attack Success Rate (ASR) from 100\% $\to$ 0.4\% while retaining over 99\% general utility; \textbf{(2) safety alignment}, localizing an alignment circuit with 3.03\% heads and 0.79\% neurons, whose removal spikes ASR from 0.8\% $\to$ 96.9\%, whereas excluding this circuit during helpfulness fine-tuning maintains 96.5\% safety retention.

cs.LG↗

arXiv2026

How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study

Emotion plays an important role in human cognition and performance. Motivated by this, we investigate whether analogous emotional signals can shape the behavior of large language models (LLMs) and agents. Existing emotion-aware studies mainly treat emotion as a surface-level style factor or a perception target, overlooking its mechanistic role in task processing. To address this limitation, we propose E-STEER, an interpretable emotion steering framework that enables direct representation-level intervention in LLMs and agents. It embeds emotion as a structured, controllable variable in hidden states, and with it, we examine the impact of emotion on objective reasoning, subjective generation, safety, and multi-step agent behaviors. The results reveal non-monotonic emotion-behavior relations consistent with established psychological theories, and show that specific emotions not only enhance LLM capability but also improve safety, and systematically shape multi-step agent behaviors.

cs.AI↗

arXiv2026

LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models

Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing methods primarily attempt to enforce length constraints by externally imposing length signals or optimization objectives, while largely overlooking the underlying limitation: the model's intrinsic deficit in length cognition. To address this, we propose LARFT (Length-Aware Reinforcement Fine-Tuning), a training framework that aligns the model's length cognition with its action. Specifically, LARFT integrates length-oriented reinforcement learning with a hindsight length awareness. By transforming on-policy data into hindsight self-awareness tasks where the model learns to identify the actual length of its own generation, LARFT jointly optimizes the model's internal representation of length information and refines its policy to satisfy length constraints, thereby achieving precise and reliable length instruction following. Extensive experiments across four base models demonstrate that LARFT outperforms existing baselines, achieving an average improvement of +20.92 points across three length instruction following benchmarks with only a marginal decline of -1.45 points on four general capability benchmarks.

cs.CL↗

arXiv2026

MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents

The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security misalignment: agents implicitly trust tools exposed by potentially untrusted MCP servers. However, despite its excellent utility, existing agents typically offer limited validation for third-party MCP servers. As a result, agents remain vulnerable to MCP-based attacks that exploit the misalignment between agents and servers throughout the tool invocation lifecycle. In this paper, we propose MCPShield as a plug-in security cognition layer that mitigates this misalignment and ensures agent security when invoking MCP-based tools. Drawing inspiration from human experience-driven tool validation, MCPShield assists agent forms security cognition with metadata-guided probing before invocation. Our method constrains execution within controlled boundaries while cognizing runtime events, and subsequently updates security cognition by reasoning over historical traces after invocation, building on human post-use reflection on tool behavior. Experiments demonstrate that MCPShield exhibits strong generalization in defending against six novel MCP-based attack scenarios across six widely used agentic LLMs, while avoiding false positives on benign servers and incurring low deployment overhead. Overall, our work provides a practical and robust security safeguard for MCP-based tool invocation in open agent ecosystems.

cs.CR↗