Fully decentralized deep learning removes global servers and ensures local data privacy. However, Euclidean consensus, averaging weights, gradients or momentum, may degrade under the situations with non-i.i.d. (non-independent and identically distributed) data and client size imbalance. We propose a geometry-aware approach based on natural gradient variational inference. Clients communicate in the expectation parameter space of an exponential family, where simple linear mixing yields a forward Kullback--Leibler (KL) barycenter consensus. The aggregate is the model closest to all client distributions, aligning updates across heterogeneous sites and mitigating distribution shift. We further provide a lightweight decentralized Adam implementation where each client maintains a diagonal Gaussian posterior and operates entirely in the expectation space for both optimization and consensus. We prove convergence for convex losses on connected graphs. On CIFAR-100 and a medical image segmentation benchmark, our method substantially outperforms Euclidean-space consensus baselines under severe non-i.i.d. and client-imbalance cases, achieving around 20% accuracy gain on CIFAR-100, while matching the communication budget and improving training stability. The code is available at https://github.com/x-lu/Beyond-euclidean-gossip.
论文检索
输入标题、作者或关键词，从 960 篇学术成果中精准定位
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
PDF ↗Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints on memory, latency, and runtime flexibility. In this work, we present a hardware-aware framework for efficient on-device inference of a LLaMA-based multilingual foundation model supporting multiple use cases on Samsung Galaxy S24 and S25 devices with SM8650 and SM8750 Qualcomm chipsets respectively. Our approach integrates application-specific LoRAs as runtime inputs to a single frozen inference graph, enabling dynamic task switching without recompilation or memory overhead. We further introduce a multi-stream decoding mechanism that concurrently generates stylistic variations—such as formal, polite, or jovial responses—within a single forward pass, reducing latency by up to 6×. To accelerate token generation, we apply Dynamic Self-Speculative Decoding (DS2D), a tree-based strategy that predicts future tokens without requiring a draft model, yielding up to 2.3× speedup in decode time. Combined with quantization to INT4 and architecture-level optimizations, our system achieves 4–6× overall improvements in memory and latency while maintaining accuracy across 9 languages and 8 tasks. These results demonstrate practical feasibility of deploying multi-use-case LLMs on edge devices, advancing the commercial viability of Generative AI in mobile platforms.
Pretrained biomedical vision–language models (VLMs) such as BioMedCLIP perform well on average but often degrade on challenging modalities where inter-class margins are small and acquisition-specific variations are pronounced, especially under few-shot supervision and when modality priors differ from pretraining corpora substantially. We propose BioVLM, a prompt-learning framework that improves cross-domain generalization without extensive backbone fine-tuning. BioVLM learns a diverse prompt bank and introduces dynamic prompt selection: for each input, it selects the most discriminative prompts via a low-entropy criterion on the predictive distribution, effectively coupling sparse few-shot evidence with rich LLM semantic priors. To strengthen this coupling, we distill high-confidence LLM-derived attributes and enforce robust knowledge transfer through strong/weak augmentation consistency. At test time, BioVLM adapts by choosing modality-appropriate prompts, enabling transfer to unseen categories and domains, while keeping training lightweight and inference efficient. On 11 MedMNIST+ 2D datasets, BioVLM achieves new state of the art across three distinct generalization settings. Codes are available at https://github.com/mainaksingha01/BioVLM.
Persuasive dialogue generation plays a vital role in decision-making, negotiation, counseling, and behavior change, yet it remains a challenging problem. In complex persuasion where the persuadee’s internal states are not expressed clearly, the persuader must interpret responses, infer the persuadee’s latent mental states (e.g., beliefs and desires), and translate them into targeted, strategy-consistent actions; however, current approaches often produce generic or weakly grounded responses even when such cues are identified. Moreover, although large language models (LLMs) can generate persuasive content, their performance varies substantially across domains due to uneven knowledge coverage and limited reasoning generalization. To address these challenges, we propose MA^{2}P, a meta-cognitive autonomous intelligent agent framework for complex persuasion. Specifically, we develop an autonomous multi-agent architecture that coordinates perception management, mental-state inference, strategy execution, memory maintenance, and performance evaluation. To mitigate cross-domain performance variation, we further design a meta-cognitive configurator that selects an appropriate meta-strategy from a structured knowledge base at the outset, thereby guiding subsequent reasoning and planning. Experimental results show that our approach achieves a higher persuasion success rate than baselines.
Mixture-of-Experts (MoE) architectures have emerged as an effective approach for scaling Large Language Models (LLMs) by activating only a subset of experts during inference. Despite their computational efficiency, MoE models incur a substantial memory bottleneck from maintaining all expert parameters during inference. To address this challenge, numerous MoE pruning methods have been proposed. However, most existing methods adopt uniform pruning across layers, which fails to capture layer-wise variations in expert importance and redundancy. In this paper, we propose COmpensated MoE Pruning with Expert-Layer distribution (COMPEL). COMPEL performs layer-adaptive expert pruning by estimating expert importance using Fisher information and deriving layer importance from layer-wise outlier distributions, enabling pruning decisions that capture layer-wise heterogeneity. Furthermore, to mitigate performance degradation resulting from expert pruning, we propose a Fisher information guided expert weight compensation method. Experimental results on the Qwen1.5-MoE-A2.7B achieve near lossless performance at 25% expert pruning and maintains performance within a 4% margin even at 50% pruning. Moreover, COMPEL consistently outperforms existing pruning methods while substantially reducing inference latency and peak GPU memory usage.
Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations
PDF ↗Natural Language Inference (NLI) datasets often exhibit human label variation. To better understand these variations, explanation-based approaches analyze the underlying reasoning behind annotators’ decisions. One such approach is the LiTEx taxonomy, which categorizes free-text explanations in English into reasoning categories. However, previous work applying LiTEx has focused on within-label variation: cases where annotators agree on the NLI label but provide different explanations. This paper broadens the scope by examining how annotators may diverge not only in the reasoning category but also in the labeling. We use explanations as a lens to analyze variation in NLI annotations and to examine individual differences in reasoning. We apply LiTEx to two NLI datasets and align annotation variation from multiple aspects: NLI label agreement, explanation similarity, and taxonomy agreement, with an additional compounding factor of annotators’ selection bias. We observe instances where annotators disagree on the label but provide similar explanations, suggesting that surface-level disagreement may mask underlying agreement in interpretation. Moreover, our analysis reveals individual preferences in explanation strategies and label choices. These findings highlight that agreement in reasoning categories better reflects the semantic similarity of explanations than label agreement alone. Our findings underscore the richness of reasoning-based explanations and the need for caution in treating labels as ground truth.
Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but existing methods suffer from critical limitations: activation addition requires careful coefficient tuning and is sensitive to layer-specific norm variations, while directional ablation provides only binary control. Recent work on Angular Steering introduces continuous control via rotation in a 2D subspace, but its practical implementation violates norm preservation, causing distribution shift and generation collapse, particularly in models below 7B parameters. We propose Selective Steering, which addresses these limitations through two key innovations: (1) a mathematically rigorous norm-preserving rotation formulation that maintains activation distribution integrity, and (2) discriminative layer selection that applies steering only where feature representations exhibit opposite-signed class alignment. Experiments across nine models demonstrate that Selective Steering achieves 5.5 higher attack success rates than prior methods while maintaining zero perplexity violations and approximately 100% capability retention on standard benchmarks. Our approach provides a principled, efficient framework for controllable and stable LLM behavior modification.
Afrispeech Semantics: Evaluating Audio–Semantic Reasoning in Spoken Language Models Across Domains and Accents
PDF ↗Audio language models (ALMs) are increasingly used for speech-based understanding; yet, their ability to perform semantic reasoning beyond transcription, Text-to-Audio Retrieval, Captioning, and Question-Answering accuracy remains insufficiently benchmarked. In particular, the effects of accent variation, domain shift, and semantic over-inference on audio reasoning are poorly understood. We evaluate audio language models across five semantic and paralinguistic reasoning tasks: entailment, consistency, plausibility, accent drift, and accent restraint. Collectively, these tasks assess a model’s ability to reason over spoken audio as the primary evidence source, including whether a textual hypothesis can be inferred, contradicted, or left undetermined by the audio, whether statements align or conflict with spoken content, whether claims are plausible given the discourse, and whether model predictions remain stable or appropriately constrained across accent variation. These findings highlight critical limitations in current audio reasoning evaluations and hope to provide guidance for more robust and equitable ALM design and assessment.
ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models
PDF ↗Test-time scaling has emerged as a transformative paradigm for enhancing the performance of large reasoning models, enabling dynamic allocation of computational resources during inference. However, as the landscape of reasoning models rapidly expands, a critical question remains: how can we systematically compare and evaluate the test-time scaling capabilities across different models? In this paper, we introduce ARISE (Adaptive Resolution-aware Scaling Evaluation), a novel metric specifically designed to assess the test-time scaling effectiveness of large reasoning models. Unlike existing evaluation approaches, ARISE incorporates two key innovations: (1) sample-level awareness that effectively penalizes negative scaling behaviors where increased computation leads to performance degradation, and (2) a dynamic sampling mechanism that mitigates the impact of accuracy fluctuations and token count instability on the final assessment. We conduct comprehensive experiments evaluating state-of-the-art reasoning models across diverse domains including mathematical reasoning, code generation, and agentic tasks. Our results demonstrate that ARISE provides a reliable and fine-grained measurement of test-time scaling capabilities, revealing significant variations in scaling efficiency across models. Notably, our evaluation identifies Claude Opus as exhibiting superior scaling characteristics compared to other contemporary reasoning models.
High-quality datasets are critical for training and evaluating reliable NLP models. In tasks like natural language inference (NLI), human label variation (HLV) arises when multiple labels are valid for the same instance, making it difficult to separate annotation errors from plausible variation. An earlier framework, VariErr (Weber-Genzel et al., 2024), asks multiple annotators to explain their label decisions in the first round and flags errors through validity judgments in the second round. However, conducting two rounds of manual annotation is costly and may limit the coverage of plausible labels or explanations. Our study proposes a new framework, EVADE, for generating and validating explanations to detect errors using large language models (LLMs). We perform a comprehensive analysis comparing human- and LLM-detected errors for NLI across distribution comparison, validation overlap, and impact on model fine-tuning. Our experiments demonstrate that LLM validation refines generated explanation distributions to more closely align with human annotations, and that removing LLM-detected errors from training data yields improvements in fine-tuning performance than removing errors identified by human annotators. This highlights the potential to scale error detection, reducing human effort while improving dataset quality under label variation.
Persona-assigned Large Language Models can adopt diverse roles, enabling personalized and context-aware reasoning. However, even minor demographic perturbations in personas, such as simple pronoun swaps, can alter reasoning trajectories, leading to divergent sets of correct answers on reasoning benchmarks. We explore the potential of these variations as a constructive resource to improve LLM reasoning performance. We propose CHOIR (Collaborative Harmonization fOr Inference Robustness), a test-time framework that harmonizes a set of demographically perturbed, persona-conditioned reasoning signals into a unified prediction. CHOIR orchestrates a collaborative decoding process among counterfactual personas perturbed across dimensions of gender, race, religion, disability, and age, dynamically balancing agreement and divergence in their reasoning paths to improve performance. Experiments demonstrate that CHOIR consistently enhances LLM reasoning across model architectures, scales, and tasks. Improvements reach up to 20.1% for individual groups and 15.1% on average, and we show that CHOIR remains effective even when base personas are suboptimal.
Tokenizers play a crucial role in determining the performance, training efficiency, and the inference cost of Large Language Models (LLMs). Designing effective tokenizers for multilingual LLMs is particularly challenging due to diverse scripts and rich morphological variation. While subword methods like Byte Pair Encoding (BPE) are widely adopted, their effectiveness in multilingual settings remains underexplored. We present MUTANT, a recipe for building multilingual tokenizers, with careful vocabulary and training data design, language-aware pre-tokenization, and subword and multiword aware training. We also introduce MUTANT-Indic, a tokenizer for India-specific multilingual LLMs, that produces linguistically coherent tokens and achieves state-of-the-art performance. Evaluated across English, Indian languages and code data, our tokenizer improves the average fertility score by 39.5% over LLaMA4 and by 18% over Sutra (the current best). This translates to 44% improvement in inference throughput over LLaMA4 while maintaining comparable performance on English and Indic benchmarks. We present detailed ablations across tokenizer training data size, vocabulary size, merging techniques, and pre-tokenization strategies, demonstrating the robustness of our design choices.
Speculative decoding has emerged as a promising paradigm for accelerating large language model inference by leveraging a lightweight draft model to generate multiple candidate tokens. However, existing methods often incur substantial training overhead to mitigate information misalignment between autoregressive draft model training and decoding. To address this challenge, we propose EDSD, an Entropy-Driven Speculative Decoding framework that uses entropy as a unified, interpretable signal for both draft model training and architectural design. EDSD drives the draft model to progressively align with the target model in an easy-to-hard manner while establishing token-level alignment as a dominant design principle. Extensive experiments on seven LLMs demonstrate that EDSD improves training efficiency by 24.8%, increases the average acceptance length by 4.0%, and achieves a 4.1% speedup compared to state-of-the-art methods. Furthermore, EDSD improves robustness to system prompt variations by more than 5x. Our findings establish entropy-driven alignment as an effective and principled foundation for efficient speculative decoding.
When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models
PDF ↗Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood. In this work, We present the first systematic multilingual evaluation of VLA models by translating the LIBERO benchmark into ten languages, revealing severe performance degradation under non-English instructions, with success rates dropping by 30–50%. Through fine-grained analysis of task executions, we find that language influence is highly non-uniform across steps: certain steps exhibit strong language dependence and dominate overall task failure, while others are largely language-agnostic. Based on this insight, we propose a step-wise inference-time intervention that aligns representations according to step language sensitivity, substantially improving performance under linguistic variation. Our results indicate that language robustness in VLA models is fundamentally a step-wise control problem, highlighting the importance of temporally structured analysis for reliable embodied agents.
Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents
PDF ↗Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more impatient, incoherent, or skeptical, can cause sharp drops in agent performance, revealing how brittle current AI agents are. Today’s benchmarks fail to capture this fragility: agents may perform well under standard evaluations but degrade spectacularly in more realistic and varied settings. We address this robustness testing gap by introducing TraitBasis, a lightweight, model-agnostic method for systematically stress testing AI agents. TraitBasis learns directions in activation space corresponding to steerable user traits (e.g., impatience or incoherence), which can be controlled, scaled, composed, and applied at inference time without any fine-tuning or extra data. Using TraitBasis, we extend τ-Bench to τ-bench, where user behaviors are altered via controlled trait vectors. We observe an average 4%–20% performance degradation on τ-bench across frontier models, highlighting the lack of robustness of current AI agents to variations in user behavior. Together, these results highlight both the critical role of robustness testing and the promise of TraitBasis as a simple, data-efficient, and compositional tool. By powering simulation-driven stress tests and training loops, TraitBasis opens the door to building AI agents that remain reliable in the unpredictable dynamics of real-world human interactions. We plan to open-source τ-bench, across four domains: airline, retail, telecom, and telehealth, so the community can systematically QA their agents under realistic, behaviorally diverse intents and trait scenarios.
Human conversation relies heavily on *conversational implicature*, in which speakers convey meanings that are suggested rather than explicitly stated. Although recent large language models (LLMs) exhibit strong conversational fluency, they remain unreliable when interpretation depends on reasoning that integrates social and contextual cues, a process rarely articulated in text. We introduce **DRinQ**, a benchmark for evaluating pragmatic reasoning about conversational implicature in question utterances, designed to isolate pragmatic variation while holding each question’s surface form fixed. To support scalable evaluation, we propose a semi-automated pipeline that produces question-context-interpretation instances with systematic variation. Across evaluations, we find a consistent generation-inference asymmetry: while state-of-the-art models can generate plausible pragmatic scenarios when guided, they often fail to recover the intended implication at inference time. For smaller models, structured prompting improves alignment with human judgments. A comparative writing study further reveals complementary strengths: human authors tend to produce safer, predictable contexts, whereas models generate varied scenarios with interpretations that sometimes exceed contextual support. These findings highlight persistent challenges in modeling conversational implicature and motivate more context-sensitive evaluation frameworks.
Chain-of-Thought (CoT) reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps. However, excessive or redundant reasoning — so-called overthinking — can increase inference costs and lead LLMs toward incorrect conclusions. In this paper, we present \textbf{REFRAIN} (\underline{REF}lective-\underline{R}edundancy for \underline{A}daptive \underline{IN}ference), a training-free framework that adaptively determines when to stop reasoning to mitigate overthinking. REFRAIN integrates a two-stage stop discriminator to identify reflective yet redundant reasoning and a sliding-window Upper Confidence Bound (SW-UCB) multi-armed bandit controller to dynamically adjust stopping thresholds according to problem difficulty without supervision or fine-tuning. Across four representative benchmarks and two model families, REFRAIN reduces token usage by 20-55% while maintaining or improving accuracy compared to standard CoT prompting. Extensive ablation and robustness analyses demonstrate its stability across models, scorers, and prompt variations. In summary, our findings highlight when-to-stop as a new and practical axis of test-time scaling — enabling models to reason not just more, but just enough.
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
PDF ↗Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal tasks, but remain susceptible to hallucinations, where generated text deviates from the underlying visual content. Existing hallucination detection methods primarily rely on output logits or external verification tools, often overlooking their internal mechanisms. In this work, we investigate the outputs of internal attention heads, postulating that specific heads carry the primary signals for truthful generation. However, directly probing these high-dimensional states is challenging due to the entanglement of visual-linguistic syntax and noise. To address this, we propose VIB-Probe, a novel hallucination detection and mitigation framework leveraging the Variational Information Bottleneck (VIB) theory. Our method extracts discriminative patterns across layers and heads while filtering out semantic nuisances through the information bottleneck principle. Furthermore, by leveraging the gradients of our VIB probe, we identify attention heads with strong causal influence on hallucinations and introduce an inference-time intervention strategy for hallucination mitigation. Extensive experiments across diverse benchmarks demonstrate that VIB-Probe significantly outperforms existing baselines in both settings. Our code will be made publicly available.
Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
PDF ↗Distractors—incorrect yet plausible answer choices in multiple-choice questions (MCQs)—are vital in educational assessments, as they help identify student misconceptions by presenting potential reasoning errors. Current distractor generation methods typically produce shared distractors for all students, ignoring the individual variations in reasoning, which limits their diagnostic effectiveness. To tackle this challenge, we introduce the task of Personalized Distractor Generation, which tailors distractors to each student’s specific cognitive flaws, inferred from their past question-answering (QA) history. While promising, this task is particularly demanding due to the limited number of QA records available for each student, which are insufficient for training, as well as the absence of their underlying reasoning process. To overcome this, we propose a novel, training-free two-stage framework. In the first stage, Monte Carlo Tree Search (MCTS) is used to reconstruct the student’s reasoning process from past errors, creating a student-specific misconception prototype. In the second stage, this prototype guides the simulation of the student’s reasoning on new questions, generating personalized distractors that resonate with their individual misconceptions. Our experiments, conducted on 1,361 students across 6 subjects, demonstrate that this approach outperforms existing methods in generating plausible, personalized distractors, and also effectively adapts to group-level settings, highlighting its robustness and versatility.
ExPerT: Personalizing LLM Responses to Users’ Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues
PDF ↗Large language models (LLMs) are increasingly used by end users, yet existing personalization methods relying on static profiles or text-only signals fail to capture query-specific expertise variation. We present ExPerT, a query-wise personalization framework that adapts LLM responses to users’ query domain expertise by combining semantic and behavioral cues. ExPerT consists of two key components: (i) a semantic–behavioral expertise inference module that jointly interprets query text and keystroke dynamics via in-context LLM prompting, and (ii) an expertise-conditioned response generation that adapts the level of detail, terminology, and conceptual complexity. Our user study with 40 participants and 1270 queries demonstrated that ExPerT reduced expertise inference error by 65.7% compared to the strongest baseline (MAE = 0.398 vs. 1.162) and improved response satisfaction by 17.52% (from 3.71 to 4.36) on a 5-point Likert scale.