Artificial Intelligence · Cross-listed from cs.CL
Position Bias Correction is Insufficient for One-Pass Attention Sorting
Qiong Tang, Xiangkun Hu, Xiangyang Liu et al. (+2 more)
Long-context
language models suffer from position bias, where information in middle positions is underutilized.
Attention Sorting addresses this by iteratively reordering documents based on
attention patterns, but its multiple sort-and-generate cycles increase deployment cost. We hypothesize that position bias is the primary bottleneck and propose Debiased One-Pass
Attention Sorting, which estimates a per-
prompt position-bias curve from the low-
attention majority of documents and uses it to correct raw
attention scores (via subtraction or division) to enable single-pass sorting. Our experiments on two models refute this hypothesis in the tested setting: on LLaMA-2-7B-32K-Instruct, debiasing produces identical results to uncalibrated single-pass sorting (94.83% containment accuracy), while on YaRN-Llama-2-7b-64k, debiasing improves accuracy by 8.67 percentage points but remains 14.84pp behind iterative sorting, closing only 37% of the gap. These results suggest that position-bias correction is insufficient to match iterative sorting, and that repeated reordering provides additional benefits beyond bias correction.
Read the full abstract ▾
All authors Qiong Tang, Xiangkun Hu, Xiangyang Liu, Yiran Chen, Yunfan Shao
Artificial Intelligence · Cross-listed from cs.CL
NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation
Qiong Tang, Xiangkun Hu, Xiangyang Liu et al. (+2 more)
Hybrid
attention models that mix full and sliding-window
attention across layers offer a promising approach to efficient long-context inference, but the critical question of which layers should retain full
attention remains unsolved. Existing methods use either fixed periodic patterns or
attention-based heuristics that may not capture what matters for downstream accuracy. We propose NLL-guided layer selection, a training-free method that directly measures each layer's importance by computing the negative log-likelihood degradation on answer
tokens when that layer uses sliding-window instead of full
attention. On LongMemEval with Qwen3-4B, our method achieves 64.6% accuracy using only 1/4 full-
attention layers, matching the 1/2-FA periodic baseline (65.0%) while halving the computational budget. NLL-guided selection outperforms the SWAA-reported periodic 1/4-FA baseline by 10.4 percentage points and a matched LightTransfer-style baseline by 26.4 percentage points. De-confounding analysis shows the signal is consistent with long-range
attention needs rather than generic layer sensitivity. The method requires only $\sim$15 minutes of one-time calibration, advancing the efficiency-accuracy Pareto frontier for long-context LLM deployment.
Read the full abstract ▾
All authors Qiong Tang, Xiangkun Hu, Xiangyang Liu, Yiran Chen, Yunfan Shao
Artificial Intelligence · Cross-listed from cs.CL
SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation
Ruochang Li, Pengcheng Huang, Zhenghao Liu et al. (+5 more)
Retrieval-augmented generation (RAG) enhances the faithfulness of large
language models (LLMs) by incorporating external knowledge into the generation process. However, conflicts between retrieved context and parametric knowledge can cause LLMs to rely on inconsistent internal knowledge, hindering their ability to faithfully leverage retrieved evidence. Existing approaches mitigate this issue by editing parametric knowledge to resolve such conflicts. However, locating and modifying knowledge encoded in model parameters is challenging and may inadvertently compromise the backbone LLM's capabilities. In this paper, we introduce SPARK, a novel framework that formulates parametric knowledge control as a latent participation policy learning problem, enabling LLMs to adaptively regulate the contribution of parametric knowledge during generation. Specifically, SPARK introduces a lightweight participation policy that dynamically modulates the contribution of FFN-mediated parametric knowledge while keeping the backbone LLM frozen. The participation policy is optimized with a faithfulness-oriented reward, enabling fine-grained control over parametric knowledge participation during generation. Extensive experiments on six
datasets validate the effectiveness of SPARK, which introduces and optimizes only 0.01% additional trainable parameters while keeping the backbone LLM fully frozen, thereby preserving its general capabilities and achieving more faithful generation than competitive baselines. All
datasets and code are available at https://github.com/OpenBMB/SHIFT.
Read the full abstract ▾
All authors Ruochang Li, Pengcheng Huang, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Yu Gu, Ge Yu, Maosong Sun
Artificial Intelligence · Cross-listed from cs.CL
Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study
Qiong Tang, Xiangkun Hu, Xiangyang Liu et al. (+2 more)
Training-free compression methods for large
language models (LLMs) often use calibration data to guide compression decisions. ROCKET, a recent method combining sparse-dictionary factorization with multi-choice knapsack problem (MCKP) allocation, derives its per-layer factorization from an output reconstruction objective but uses weight-space Frobenius error as the MCKP allocation cost. We investigate whether aligning the allocation cost with the output-space objective improves compressed model fidelity. On Qwen3-8B at 50% compression, our ROCKET-ActCost achieves +0.8 percentage points higher average accuracy across 8 zero-shot
benchmarks (53.1% vs 52.3%), but increases WikiText perplexity by 16% (61.46 vs 52.98). This accuracy-perplexity tradeoff reveals that different allocation objectives favor different downstream metrics. The high correlation ($>$0.99) between weight-space and output-space errors limits allocation divergence, explaining the modest effect size. On Llama-3.2-1B at 20% compression, the two methods produce near-identical results (53.3% vs 53.5% accuracy, 14.45 vs 14.66 PPL), suggesting that the effect of the cost function is minor at lower compression ratios.
Read the full abstract ▾
All authors Qiong Tang, Xiangkun Hu, Xiangyang Liu, Yiran Chen, Yunfan Shao
Artificial Intelligence · Cross-listed from cs.CV
Improving Adversarial Robustness via Activation Amplification and Attenuation
Taïga Gonçalves, Yongsong Huang, Tomo Miyazaki et al. (+1 more)
The existence of
adversarial attacks is often attributed to the presence of non-robust features in neural networks. While prior defenses reduce their impact via
pruning, masking, or feature recalibration, we instead propose to jointly learn to amplify and attenuate these signals through a simple activation scaling mechanism. To this end, we introduce Activation Amplification and Attenuation (A3), a lightweight plug-in module that enhances
adversarial robustness with minimal modifications of the activations. A3 dynamically rescales the activations using a learnable mask and a scaling factor derived from the original activation magnitudes. The influence of
adversarial perturbations can be amplified or attenuated using the same learnable parameters by simply flipping the sign of the scaling operation. The amplified signals serve as negative references to construct novel contrastive and ranking loss functions. Experimental analysis shows that learning to degrade the predictions in amplification mode simultaneously improves
adversarial robustness in attenuation mode. Moreover, A3 relies on only a small number of learnable parameters, with most of its behavior being determined by the scaling mechanism rather than additional network capacity. Extensive experiments demonstrate that integrating A3 into different backbones,
datasets, and training methods consistently improves
adversarial robustness while introducing negligible computational and
memory overhead compared to existing plug-in modules. Code is available at: https://github.com/tgoncalv/A3.
Read the full abstract ▾
All authors Taïga Gonçalves, Yongsong Huang, Tomo Miyazaki, Shinichiro Omachi
Artificial Intelligence
Understanding Rollout Error in Graph World Models
Xinyuan Song and Zekun Cai
World models are increasingly used for planning by predicting future states under candidate actions. Many planning environments, however, are naturally graph-structured, with
agents, tools, skills, routes, and dependencies connected through fixed or evolving relations. Understanding how prediction errors accumulate in such graph-structured rollouts is therefore critical for reliable long-horizon planning.In this work, we systematically study how rollout errors propagate in Graph World Models (GWMs). We analyze both fixed- and dynamic-edge regimes and derive
topology-aware error bounds that characterize the roles of graph structure, learned dynamics, and evolving edges. We then validate these theoretical findings across synthetic graph
topologies and heterogeneous
agent-graph testbeds, showing that rollout error and planning regret increase with horizon and that dynamic-edge training is important when graph structure evolves. Together, these results characterize when GWMs remain reliable under long-horizon planning and when graph structure amplifies rollout errors. Motivated by these findings, we propose Error-Aware GWM, which combines spectral regularization, rollout consistency, and critical-node weighting, and improves long-horizon stability without sacrificing one-step accuracy. Experiments show that Error-Aware GWM consistently improves long-horizon rollout stability without sacrificing prediction accuracy.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
Shiqiang Gong
Offline reinforcement learning enables policy learning from fixed
datasets without additional environment interaction, making it appealing for safety-critical applications where online exploration is costly or unsafe.
Diffusion-based decision-making methods have recently achieved strong performance in offline RL by modeling rich,
multimodal trajectory distributions. However, existing
diffusion planners are typically risk-neutral and therefore may overlook rare but catastrophic outcomes that are crucial in real-world deployment. In this work, we propose RS-Diffuser, a risk-sensitive offline
diffusion planning framework that combines
diffusion-based trajectory generation with distributional value critics. RS-Diffuser learns a
diffusion planner over future state trajectories, a separate inverse dynamics model for action decoding, and a Monte Carlo distributional critic that estimates the full return distribution of candidate plans through
quantile regression. At sampling time, we incorporate a risk-sensitive guidance signal into the denoising process, using gradients computed from tail-aware objectives such as Conditional Value at Risk to steer generation toward desired risk profiles. As a result, a single trained model can flexibly produce risk-averse, risk-neutral, or risk-seeking behaviors by changing only the inference-time risk parameter. Extensive experiments on risk-sensitive D4RL and risky
robot navigation benchmarks demonstrate that RS-Diffuser achieves state-of-the-art performance, improving both overall return and worst-case robustness while reducing safety violations.
Read the full abstract ▾
Artificial Intelligence
Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework
Jiajing Zhang, Jiamei Jiang, Chenyang Zhang et al. (+3 more)
Large
language models (LLMs) have attracted widespread
attention from academia and industry, yet their deployment raises critical security concerns regarding robustness and reliability. Planning, a core component of intelligent behavior, remains challenging for LLMs, which often produce infeasible or incorrect solutions in long-horizon decision-making tasks due to inherent complexity. In this paper, we propose a symbolic feedback-driven iterative self-refinement framework to enhance the robustness and reliability of LLMs in long-horizon planning. Specifically, a natural
language prompting mechanism is introduced to map logical symbols into natural
language descriptions, enabling LLMs to better capture task constraints and semantics. We further design a symbolic verifier that identifies errors and converts them into corrective instructions interpretable by the LLM, thereby guiding self-refinement. In addition, we leverage a plan recognizer to infer goal reachability, facilitating more effective guidance toward desired goals. Empirical results demonstrate that the proposed framework consistently improves both feasibility and correctness in long-horizon planning tasks. This highlights its effectiveness in enhancing the reliability of LLM-based planning and potential to enable more trustworthy AI systems.
Read the full abstract ▾
All authors Jiajing Zhang, Jiamei Jiang, Chenyang Zhang, Feifei Mo, Linjing Li, Daniel Zeng
Artificial Intelligence · Cross-listed from cs.RO
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
Guoheng Sun, Kaixi Feng, Shwai He et al. (+8 more)
Vision-
Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized
language backbones from pretrained VLMs whose capacity far exceeds what is needed for short robotic instructions. This raises a basic question: how much of a VLA model is actually necessary for closed-loop control? In this work, we study architectural redundancy in VLA models by using
transformer block removal as a controlled intervention. We introduce Drop-Then-Recovery (DTR), an analysis protocol that removes selected blocks from a pretrained VLA model and then fine-tunes the resulting model to measure whether the removed capacity was necessary for downstream control. To make this intervention reliable, we propose GateProbe, a one-shot virtual-gate sensitivity metric that ranks blocks by their contribution to the downstream action loss. Across multiple VLA architectures, manipulation
benchmarks and even real-
robot industrial scenarios, we find a strong asymmetry in post-removal recoverability: \ul{
language backbones are highly redundant for standard robotic manipulation tasks, whereas
vision and action pathways are substantially less tolerant to removal}. On LIBERO, removing half of the LLM blocks even improves OpenVLA-OFT from 95.0% to 98.3% under the same downstream fine-tuning budget, and retaining only two
language blocks still recovers baseline-level performance. These results suggest that current VLA
benchmarks may exert limited pressure on deep
language grounding and compositional instruction understanding, and that future VLA architectures should allocate capacity more deliberately across
language,
vision, and action components. The code is available at https://github.com/s1ghhh/VLADrop.
Read the full abstract ▾
All authors Guoheng Sun, Kaixi Feng, Shwai He, Xiaochuan Gong, Yexiao He, Ziyao Wang, Zheyu Shen, Wanghao Ye, Ramana Rao Kompella, Gaowen Liu, Ang Li
Artificial Intelligence · Cross-listed from cs.SD
From General-Purpose Audio Tagging to Spatially Grounded Sound Event Localization and Detection
Stefano Giacomelli, Stefano Damiano, Claudia Rinaldi et al. (+2 more)
This report investigates the extension of pretrained General-Purpose Audio Tagging (GP-AT) models toward spatially grounded Sound Event Localization and Detection (SELD). The proposed AT2SELD framework couples a pretrained AT backbone with compact First-Order Ambisonics (FOA) spatial processing, track-wise SED and Cartesian DOA estimation, permutation aware supervision, and calibration. It characterizes how semantic audio priors support localization-aware scene analysis under data, computation, and deployment constraints. The framework is developed through informed multi-stage Neural Architecture Search (NAS). Stage 1 shows that spectral FOA descriptors, based on magnitude, phase, and Intensity Vectors (IVs), provide the most reliable interface for semantic-to-spatial transfer. Stage 2 identifies early residual spatial encoding as the main capacity-sensitive component, while late track-wise abstraction and recurrent smoothing act mainly as refinement stages. Stage 3 shows that late cross-stitch coupling improves semantic-spatial interaction, whereas early fusion is costlier and less effective. Diagnostic evaluation analyzes the selected architecture under class balancing, focal loss, activity-conditioned DOA supervision, threshold calibration, and transfer across STARSS23, TAU2019, TAU-NIGENS2020, and TAU-NIGENS2021. Focal loss improves the activity point, active-only DOA supervision mitigates inactive target dominance, and validation-selected thresholds recover calibration without replacing spatial learning. Cross-
dataset and oracle-activity analyses indicate strong fixed source localization on TAU2019, transferable representations from TAU NIGENS2021, and meaningful but uncertain behavior on STARSS23. Overall, GP-AT priors appear promising for SELD design when embedded in spatial-aware architectures and optimized through integrated calibration and deployment oriented strategies.
Read the full abstract ▾
All authors Stefano Giacomelli, Stefano Damiano, Claudia Rinaldi, Fabio Graziosi, Toon van Waterschoot
Artificial Intelligence · Cross-listed from cs.LG
Flexformer: Flexible Linear Transformer with Learnable Attention Kernel
Haoran Zhang and Feng Zhou
Transformer models rely on
attention mechanism to capture long-range dependencies but suffer from quadratic complexity, limiting their scalability to long sequences. Kernel-based linear
attention reduces this complexity but typically relies on fixed or weakly learnable kernels, restricting expressiveness and performance. In this work, we propose Flexformer, a flexible linear
Transformer that learns
attention kernels in a fully data-driven manner. Flexformer builds on random
Fourier feature-based linear
attention and treats spectral frequencies as trainable parameters, enabling the model to learn a broad family of
attention kernels. We develop both stationary and nonstationary variants, with the latter offering strictly greater expressiveness. Extensive experiments on
language modeling and sequence classification demonstrate that Flexformer consistently outperforms baselines. Moreover, Flexformer can be effectively distilled from pretrained
Transformers to recover softmax
attention and exhibits strong kernel transferability across domains, achieving both high efficiency and competitive performance on long-sequence tasks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference
Yuhang Chen, Jinhao Duan, Ruichen Zhang et al. (+11 more)
Large
Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment. However, real-world cloud infrastructure is inherently dynamic, characterized by fluctuating availability (e.g., spot instance preemption) and tiered Quality-of-Service requirements. In such volatile settings, static models are inflexible: they either crash under resource constraints or waste compute on redundant operations. To bridge this gap, we propose Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference. Unlike prior methods that condition only on input difficulty, we formulate inference as a constrained allocation problem conditioned on both the input and the runtime resource budget itself. We introduce lightweight, budget-conditioned and input-aware gating networks integrated into the LLM. These gates are trained via a unified objective that jointly optimizes task performance, logical consistency, and resource costs along three axes matching how real-world dynamics manifest: layer skipping for
memory and depth pressure, head
pruning for throughput contention, and
reasoning-
token reduction for latency tightening. This lets the model learn a budget-aware policy beyond input difficulty alone: it adaptively configures its computational footprint with respect to real-time resource dynamics, maximizing
reasoning depth when resources permit while enforcing strict frugality when budgets tighten. A single L2A model traces the entire compute-accuracy Pareto frontier on Llama-3-8B and Qwen-3-4B: at up to 34% realized layer sparsity, it stays within 0.6% of the dense baseline on GSM8K, with the same gap holding zero-shot on out-of-distribution tasks, while every static or heuristic baseline requires a separately tuned model and still drops by 5-10% at comparable inference time.
Read the full abstract ▾
All authors Yuhang Chen, Jinhao Duan, Ruichen Zhang, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Parish Aggarwal, Frank Shyu, Luke Simon, Sandeep Pandey, Tianlong Chen, Xi Liu
Artificial Intelligence · Cross-listed from cs.CL
KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems
Minjun Choi, Yerin Kim, Junghyuk Seo et al. (+3 more)
Enterprise Knowledge Graphs (KGs) are increasingly used for internal search, analytics, and question answering, but building natural-
language interfaces for private enterprise graphs remains costly. We present KG2Cypher, a data-centric pipeline for building enterprise text-to-Cypher systems from existing KGs. KG2Cypher first constructs an executable Cypher query from observed graph facts and then uses LLMs to generate its associated natural-
language question. The resulting Text-Cypher pairs are validated with an LLM judge and human validation, and are converted into candidate-aware SFT data. The trained generator is served with class-conditioned schema prompting, entity
retrieval, and LoRA-based inference. We evaluate KG2Cypher in Korean enterprise settings, where short search-style queries and schema paraphrases make
language grounding difficult. LoRA SFT improves execution-result F1 from 0.806 to 0.950 on broadcast-program queries and from 0.70 to 0.92 on company queries. In an 11-class setting, KG2Cypher achieves 95.2% exact match, 99.9% execution rate, and 0.964 execution-result F1.
Read the full abstract ▾
All authors Minjun Choi, Yerin Kim, Junghyuk Seo, Sujin Mo, Hyemin Lee, Youngjoong Ko
Artificial Intelligence
ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
Zhaoqi Wang, Zijian Zhang, Kun Zheng et al. (+4 more)
The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-generated misinformation under Generative Engine Optimization (GEO) poisoning allows adversarially crafted content to be systematically surfaced by
retrieval systems, contaminating LLM
reasoning. In this paper, we propose Tree of Evidence (ToE), a hierarchical evidence
reasoning framework for automated fact-checking that models each claim as a dynamically expanding argument tree. ToE integrates a reinforcement learning-driven multi-source
retrieval agent, an evidence evaluation
agent, and an argument tree aggregation
algorithm to iteratively decompose, retrieve, and verify claims through an explainable evidence chain. We further provide a theoretical analysis of the
retrieval process, deriving a formal error bound that guarantees the learned policy converges to a neighborhood of the information-theoretically optimal policy. Experiments across multiple
datasets and backbone LLMs demonstrate that ToE achieves improvements ranging from 4 to 24 percentage points over competitive baselines, with particularly pronounced gains on adversarially poisoned inputs.
Read the full abstract ▾
All authors Zhaoqi Wang, Zijian Zhang, Kun Zheng, Zhen Li, Xin Li, Chunlei Li, Jiamou Liu
Artificial Intelligence · Cross-listed from cs.IR
Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation
Yuhang Chen, Xianfeng Wu, Jinhao Duan et al. (+11 more)
Discrete
diffusion language models (dLLMs) recover masked
tokens in parallel, offering significant speedups over autoregressive (AR) generation. However, such promising frameworks face a fundamental architectural design dilemma: \ding{182} Adopting bidirectional
attention achieves strong generation quality by allowing each position to access the full context, but is inherently incompatible with KV caching, limiting inference throughput in batch-serving scenarios; \ding{183} Conversely, causal
attention enables efficient cached inference but loses all right-side context, substantially degrading generation quality. This paper introduces Bifocal dLLMs, a new paradigm that resolves this dilemma through asymmetric bidirectional context. Analogous to bifocal lenses, we instantiate the paradigm as R2LM (Right-to-Left Mamba), which combines two complementary mechanisms: $a$) standard causal
attention providing precise left-context with full KV cache compatibility, while $b$) a lightweight reverse Mamba SSM sidecar supplying compressed right-side context without breaking cacheability. Comprehensive experiments on continued pretraining of Qwen3-1.7B with 60B
tokens demonstrate that R2LM achieves $2.4\times$ to $12.9\times$ higher throughput than bidirectional dLLMs and $1.9\times$ to $2.9\times$ speedup over AR baselines in batch serving through parallel decoding with KV caching, while exceeding the causal baseline on most
benchmarks and surpassing the bidirectional dLLM on average.
Read the full abstract ▾
All authors Yuhang Chen, Xianfeng Wu, Jinhao Duan, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Parish Aggarwal, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Tianlong Chen
Artificial Intelligence · Cross-listed from cs.CL
Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
Zhuo Zuo, Li Yue, Wenhao Zheng et al. (+2 more)
Despite their strong general capabilities, large
language models (LLMs) often remain unreliable when outputs must be numerically precise. A key reason is the training objective: standard cross-
entropy treats numeric
tokens as unstructured categories and ignores the metric structure of their values. We address this mismatch with Smooth Maximum Mean Discrepancy (SMMD), which builds on the classic MMD by incorporating value-distance kernels over numeric
tokens and graph-based smoothness. With this kernel defined over a numeric sub-vocabulary, SMMD aligns the predicted numeric distribution to the target via kernel matching and smooths the prediction-target residual over the induced kernel graph to encourage local consistency. We evaluate SMMD on four numeric-target tasks: mathematical
reasoning, arithmetic calculation, clock-time recognition, and chart question answering, across multiple open-weight LLM and VLM backbones. SMMD consistently improves accuracy over both cross-
entropy and recent numeric-target losses; analyses show complementary effects between MMD and smoothness and underscore the importance of distance-based kernel design. Code is available at https://github.com/Zuozhuo/smmd-loss.
Read the full abstract ▾
All authors Zhuo Zuo, Li Yue, Wenhao Zheng, Chenpeng Wang, Xianggen Liu
Artificial Intelligence · Cross-listed from cs.CL
Megan Wei, Deepali Aneja, Jiaqi Su et al. (+3 more)
Prosodic emphasis varies across
languages,
emotions, and speaking styles, yet existing emphasis detection models are largely trained and evaluated on monolingual neutral read
speech. We introduce MMEE (
Multilingual Multi-
Emotion Emphasis), a corpus of 10,000 professionally recorded expressive utterances (14.13 hours) across 7
languages and 34
emotion/style categories, with three-level perceptual labels (10 annotations per sample). We
benchmark two state-of-the-art architectures under monolingual, cross-lingual,
multilingual, cross-
emotion, cross-
dataset, and data-scale settings. Monolingual models show limited zero-shot transfer, degrading across typologically distant
languages, while
multilingual training substantially improves robustness. Models transfer robustly between high- and low-arousal
emotions; bidirectional transfer between synthetic and perceptual
benchmarks suggests shared prosodic structure; and performance stays robust even at smaller training scales.
Read the full abstract ▾
All authors Megan Wei, Deepali Aneja, Jiaqi Su, Yunyun Wang, Haonan Chen, Zeyu Jin
Artificial Intelligence · Cross-listed from cs.LG
The Simulacrum: Decision-Theoretic Pretraining for Near-Optimal Time-Series Forecasting and Inference
Pablo Montero-Manso and Marcel Scharth
We introduce a neural network-based framework for learning time series
estimators through a process we term decision-theoretic pretraining. Analysts specify a generative world, a distribution over data-generating processes, and a target decision objective. A neural network trained on stratified simulations from this world approximates the corresponding optimal decision rule, yielding a neural
estimator that provides forecasts, parameter estimates, predictive intervals, or model-selection for zero-shot inference on previously unseen time series. The joint specification of the generative world and objective enables the
estimators to directly approximate process-level, finite-sample properties: near-optimal risk, bias control, minimax performance, and uniform calibration. Our experiments demonstrate that these neural
estimators can outperform traditional baselines such as maximum likelihood estimation and model selection via AICc, for the same model structural model classes. Furthermore, even when trained purely on simulations of structural models, they achieve competitive or state-of-the-art
forecasting accuracy on major real-world
benchmarks, compared with statistical, neural or large pre-trained models. We illustrate the framework by addressing two longstanding challenges: finite-sample bias and miscalibration in AR(p) models, and the forecast combination puzzle. These applications highlight the approach's main advantage: its ability to approximate solutions to analytically intractable or computationally prohibitive time series problems, including complex structural equations or optimality criteria. Ultimately, by enabling explicit control over decision-theoretic trade-offs, the framework equips analysts with highly efficient estimation tools tailored to their specific analytical needs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning
Austin MY Cheung and Yi Yang
Recent work has shown that fine-tuning large
language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We investigate a related but distinct failure mode: warmth fine-tuning also weakens
adversarial safety, making models more susceptible to jailbreaks and harmful output generation. We examine whether this reflects an inherent consequence of empathetic adaptation or an artifact of data construction. To address this, we introduce a persona-driven rewriting pipeline that conditions user turns on low agreeableness and pairs this with warm, de-escalating assistant responses. Across three experiments on four models, our approach reduces jailbreak susceptibility and harmful output rates relative to generic warmth fine-tuning baselines, while preserving conversational warmth. Representational probing provides suggestive evidence that this conditioning reduces the
geometric alignment between warmth and compliance directions in latent space. These results show that safer empathetic fine-tuning is achievable through data design alone, without safety labels, harm detectors, or changes to the training objective.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks
Andrew C. Cullen, Neil G. Marchant, Jiani Xie et al. (+4 more)
While voice control is rapidly becoming a ubiquitous vector of human-AI communication, the risks facing these systems remain poorly understood. This is, in part, a product of the difficulties in scaling strictly digital
adversarial workflows to the physical world. These scale barriers have led the community to abstract away key acoustic factors relating to detectability and the influence of geometry on acoustics. These methodological and metrological shortcomings undermine our understanding of risk. We illuminate these issues through real-world testing, conceptual discussions, and a novel, high-throughput reality simulation framework. By testing over 8 million
adversarial evaluations, we demonstrate that acoustic awareness yields relative Word Error Rate increases of up to 94.5% under Whisper and wav2vec. We employ this framework to explore a formalize and operationalize a Dual-Form Signal to Noise Ratio to decouple source stealth from victim attack efficacy, resolving a crucial limitation in current works. This lays the groundwork for repeatable, verifiable research that embraces, rather than abstracts, the acoustic environment.
Read the full abstract ▾
All authors Andrew C. Cullen, Neil G. Marchant, Jiani Xie, Paul Montague, Sean Lamont, Maxwell Standen, Benjamin I.P. Rubinstein
Artificial Intelligence · Cross-listed from cs.LG
What Was That Again? Certified Robustness for Automatic Speech Recognition
Andrew C. Cullen, Neil G. Marchant, Jiani Xie et al. (+2 more)
Automatic
Speech Recognition systems are notoriously both sensitive to
adversarial and benign perturbations. While this has been repeatedly demonstrated using reference
datasets, detecting such behaviors in deployed systems is incredibly challenging, due to the absence of oracle knowledge of the true transcription. We demonstrate that employing a certification-inspired mechanism can significantly decrease WER, increase recall, and decrease the Spearman correlation between confidence and WER. We achieve this through a dual-gate diagnostic pipeline: a Two-Sided Atomic Audit that accumulates statistical wealth to certify both
token existence and
adversarial exclusion, and a Rank-Based Tournament that selects the winning sequence. Our evaluations across four diverse architectures demonstrate up to a 55% relative reduction in Word Error Rate, while also providing granular word- and sentence-level certifications to enhance acoustic security.
Read the full abstract ▾
All authors Andrew C. Cullen, Neil G. Marchant, Jiani Xie, Paul Montague, Benjamin I.P. Rubinstein
Artificial Intelligence · Cross-listed from cs.LG
Class-frequency Guided Noise Schedule for Diffusion Models
Jiequan Cui, Beier Zhu, Qingshan Xu et al. (+3 more)
In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within
diffusion models. For score-based generative models, low-density regions often lead to inaccurately estimated scores, thereby compromising the generation quality. Although the multi-scale noise schedule can alleviate this issue during the
diffusion process, low-frequency classes still face the challenge of large low-density regions, resulting in more inaccurate estimated scores than high-frequency classes. Furthermore, high-frequency classes tend to dominate the score space, causing a convergence of most data points towards generating samples from these classes. Consequently, samples generated within low-frequency classes exhibit suboptimal quality and limited diversity. To address this challenge, we propose the Class-frequency Guided (CFRG) noise schedule, leveraging the insight that low-frequency classes should be endowed with larger-scale noises. To illustrate the effectiveness of our method, we conduct experiments on various tasks, including image generation, image classification, and text-to-image generation, using imbalanced
datasets, i.e., CIFAR-100-LT, and ImageNet-LT. By employing the CFRG noise schedule, we achieve substantial improvements over baselines, manifesting the crucial role of frequency statistics in noise schedule design.
Read the full abstract ▾
All authors Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaojuan Qi, Bei Yu, Hanwang Zhang
Artificial Intelligence · Cross-listed from cs.LG
Halt Fast! Early Stopping for Certified Robustness
Andrew C. Cullen, Paul Montague and Benjamin I.P. Rubinstein
Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited by extreme computational costs. Standard RS requires tens of thousands of model evaluations per input and forces practitioners to commit to fixed sample sizes a priori. In this work, we present a novel meta-learning framework for anytime-valid certified robustness that adaptively deploys computational resources. By using a lightweight meta-learner to predict image-specific priors for a sequential E-process, we achieve a 20-fold reduction in sample complexity compared to traditional methods while maintaining rigorous statistical guarantees. Beyond raw efficiency, we demonstrate how anytime-validity enables adaptively allocating compute based upon application-specific risk thresholds, a form of resource triage impossible under classic certification frameworks. That this is achievable while also providing similar certification performance demonstrates that our approach provides a pathway for real-time, safety-critical certification deployments.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Deployment-Side Adaptiveness in Multi-Horizon Volatility Forecasting
Riku Green, Zahraa S. Abdallah and Telmo M Silva Filho
In financial
forecasting, predictive performance depends not only on which model is trained, but also on how the trained model is deployed. We study this issue in multi-horizon
volatility forecasting. Our starting point is that a trained multi-output (
MIMO) forecaster does not define a single deployable predictor: by changing the inference-time rollout rule, the same trained model induces a family of forecasts with different accuracy and cost profiles. Across 20 stock-
volatility series, three forecast horizons, and architectures ranging from linear models to PatchTST, we find that non-default rollout rules often improve over standard
MIMO deployment. However, the best fixed rule varies substantially across architectures and horizons, making any single static replacement unreliable. We therefore evaluate validation-based deployment policies over the induced rule family. Under the primary MSE objective, validation-selected singletons provide a low-cost improvement over default
MIMO, while small rule subsets recover much of the benefit of larger ensembles at substantially lower inference cost. We also find that policy rankings are metric-sensitive: MSE-selected policies do not transfer uniformly to QLIKE, a finance-standard
volatility loss. These results show that inference-time deployment is a meaningful source of adaptiveness in financial
forecasting, and that trained
volatility forecasters should be evaluated not only by their architecture, but also by their deployment policy.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Mitigating LLM-based p-Hacking by Preregistering for the Next LLM
Maria Thomas, Kristina Gligoric and Nihar B. Shah
Large
language models (LLMs) are increasingly used to generate, classify, and annotate data whose outputs feed downstream hypothesis tests. However, LLM-based research is easy to p-hack: a researcher can tune the
prompts, decoding parameters, or output format until a desired result is reached. We propose a protocol to mitigate p-hacking in LLM-based research: preregistering the experiment and eligible models, and then running it on the first eligible LLM that is released after the preregistration. The researcher finalizes the procedure on current models, preregisters the analysis plan together with a set of eligible future models, and runs the confirmatory analysis on the first eligible model released afterward. Because this model does not exist at commitment time, it cannot be hacked against; furthermore, configurations that hack one model frequently do not transfer to the next. We evaluate the protocol on two tasks whose true values are known. Across 20 models from four providers and 11 LLM-analysis configurations, the protocol would have blocked successful transfer of the p-hack in 73.9% and 72.7% of cases in the two tasks. Additional analyses reveal that mitigation remains substantial under several stress tests. Finally, putting money where our mouth is, we followed our own protocol and preregistered our experiment. The preregistered experiment confirmed the protocol's effectiveness: out of the 7 configurations that hacked the prior model, the hacking failed to carry over in 6 configurations on the first eligible model released afterward.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence
Zhiqiang Xie, Yijing Lin, Zhipeng Gao et al. (+1 more)
Edge devices increasingly invoke large
language models (LLMs) through API services for context aware edge intelligence, while edge generated data may be collected to improve LLMs and may introduce sensitive, copyrighted, harmful, or outdated information into model behavior. Machine unlearning offers a practical way to remove the influence of undesired data without retraining LLMs. However, existing methods still face two gaps. The first is API only black box access, where target model parameters and internal logits are unavailable. The second is how to preserve retained utility when unlearning target data and retained data share highly similar
prompt structures or semantic patterns. To address these challenges, we propose Controlled Behavioral Divergence (CBD), an API only black box unlearning framework. CBD uses two auxiliary models to create controlled behavioral divergence between retained inputs and unlearning target inputs, converts this divergence into an unlearning relevance score, and routes unlearning related
prompts away from the target LLM. To improve discrimination accuracy under high similarity between target and retained data, CBD constructs a gradient statistics based discriminative basis by estimating empirical Fisher
matrices and solving a regularized generalized
eigenvalue problem, guiding the unlearning signal toward target specific information rather than shared
prompt structures. Compared with eleven white box and gray box unlearning baselines, CBD achieves a better unlearning utility trade off and its performance varies little across settings. On ToFU forget10, CBD approaches the retrained reference on the forget set while raising model utility to 74.90, about 15% above the second best baseline. On WMDP, it lowers hazardous knowledge accuracy to 25.68, near random guessing, while preserving MMLU accuracy of 52.67. Code is at https://github.com/DGL-codes/CBD.
Read the full abstract ▾
All authors Zhiqiang Xie, Yijing Lin, Zhipeng Gao, Dong In Kim
Artificial Intelligence · Cross-listed from cs.CL
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen et al. (+3 more)
Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect
hallucinations in Large
Language Models (LLMs) by learning uncertainty from internal model signals. Yet, recent methods vary simultaneously across feature design, training data construction, and evaluation setting, obscuring what actually drives performance. To address this issue, we propose a factorised study of probe-based UE under matched conditions. Our results show that raw hidden states and
attention features are difficult to outperform in-domain. However, under distribution shift, structured and compressed features are more robust, suggesting that in-domain performance alone is insufficient to measure progress. Furthermore, prompting and label construction significantly affect probe behaviour. Building on these empirical design principles, we construct
benchmark-pretrained probes that retain useful discriminative signal on open-ended factual generation. Their competitive performance relative to limited-label target setting probes and sampling-based
estimators suggests that they can provide a practical starting point for subsequent target-domain adaptation. More broadly, our work encourages deployment-oriented evaluation of probe-based uncertainty
estimators.
Read the full abstract ▾
All authors Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen, Quang Minh Nguyen, Duc Anh Vu, Anh Tuan Luu
Artificial Intelligence · Cross-listed from cs.CV
Explainable AI for Biodiversity Monitoring and Ecological Image Analysis
Brinnae Bent, Holly R. Houliston, Jiayi Zhou et al. (+2 more)
Artificial intelligence is transforming biodiversity monitoring by enabling automated analysis of ecological imagery collected from camera traps, drones, satellites,
underwater platforms, and other sensing systems. These tools can expand the scale and speed of conservation assessments, yet many computer
vision models remain difficult to inspect, making it challenging to determine whether predictions are based on ecologically meaningful signals or on spurious correlations, sampling biases, and other artifacts that may undermine conservation decisions. We argue that explainable artificial intelligence (XAI) should become a standard component of ecological model validation because conservation practitioners increasingly depend on understanding not only whether a model is accurate, but why it is accurate. We provide practical guidance for applying XAI to three common ecological computer
vision tasks: image classification, object detection, and image
segmentation. To illustrate how XAI can support ecological model
auditing, refinement, and deployment, we present two case studies using aerial imagery: harbor seal detection and cetacean anatomical
segmentation. These examples demonstrate how explanation methods can identify biologically meaningful cues, reveal false positives driven by background and shape confounds, uncover edge and occlusion effects, and guide data collection, augmentation, and retraining strategies. More broadly, they show how explainability can help assess whether model
reasoning aligns with ecological understanding. We conclude by identifying key challenges and opportunities. By making model behavior more transparent and scientifically interrogable, XAI can help ensure that AI-supported ecological evidence is more reliable, understandable, and actionable for biodiversity conservation.
Read the full abstract ▾
All authors Brinnae Bent, Holly R. Houliston, Jiayi Zhou, Günel Aghakishiyeva, David W. Johnston
Artificial Intelligence · Cross-listed from q-bio.GN
Reconstructing the Developmental Trajectory of Adipocytes in Human Adipose Tissue Using Single-Cell RNA Sequencing
Weny S. M Sitinjak and Humasak Tommy Argo Simanjuntak
Obesity is a global health crisis associated with metabolic disorders such as type 2 diabetes and cardiovascular disease. This study employed single-
cell RNA sequencing to reconstruct the developmental trajectory of human adipocytes from adipose tissue samples. Our analysis identified 15 transcriptionally distinct
cell clusters, including 7 transitional states, revealing the dynamic process of adipocyte differentiation. We detected 16 functionally active signaling pathways mediating cellular communication between adipocytes and their progenitors. Among these, insulin-like growth factor (IGF) and fibroblast growth factor (FGF) pathways emerged as the most prominent networks, showing consistent activity across differentiation stages (p<0.05). The study revealed depot-specific differences, with visceral adipocytes undergoing additional extracellular
matrix remodeling absent in subcutaneous differentiation. Spatial analysis further showed that IGF signaling was particularly active in perivascular niches, while FGF activity dominated in mature adipocyte zones. These results provide the first comprehensive map of human adipocyte development, highlighting IGF and FGF pathways as potential therapeutic targets. The identified signaling networks offer new insights for developing interventions to promote healthy adipose expansion or inhibit pathological fat accumulation. This work advances our fundamental understanding of adipose tissue biology while providing clinically relevant data for metabolic disorder treatments.
Read the full abstract ▾
Artificial Intelligence
Zhiyuan Han, Beier Zhu, Wenwen Tong et al. (+8 more)
We find that explicit
reasoning does not necessarily translate into better
multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable. Specifically, for
reasoning-based MLLMs, fast thinking by triggering direct answers often outperforms slow thinking after deliberative
reasoning. Our empirical analyses show that fast thinking improves recall with broader and more confident predictions, whereas slow thinking favors precision through conservative filtering of incorrect categories. Building on these insights, we propose MER-R1, a reinforcement learning framework that turns slow-fast complementarity into explicit optimization. Dual-objective disentanglement separates recall and precision into two optimization signals, allowing them to be jointly optimized rather than traded off against each other. Slow-fast confidence calibration further aligns the final slow-thinking answer with fast-thinking intuition, strengthening correct
emotions while suppressing incorrect ones. In this way, MER-R1 unifies the recall-oriented intuition of fast thinking with the precision-oriented selectivity of slow thinking. We further provide theoretical justification for this synergy, showing that it mitigates variance-induced interference during optimization. Extensive experiments on MER-UniBench and MME-
Emotion show that MER-R1 achieves state-of-the-art performance and makes
reasoning genuinely benefit
emotion recognition.
Read the full abstract ▾
All authors Zhiyuan Han, Beier Zhu, Wenwen Tong, Chengwei Qin, Xinyi Wang, Jiayu Zhang, Jiangnan Chen, Hewei Guo, Dongchuan Ran, Lewei Lu, Xun Yang