As large language models (LLMs) become increasingly integrated into personal writing tools, a critical question arises: can LLMs faithfully imitate an individual's writing style from just a few examples? Personal style is often subtle and implicit, making it difficult to specify through prompts yet essential for user-aligned generation. This work presents a comprehensive evaluation of state-of-the-art LLMs' ability to mimic personal writing styles via in-context learning from a small number of user-authored samples. We introduce an ensemble of complementary metrics-including authorship attribution, authorship verification, style matching, and AI detection-to robustly assess style imitation. Our evaluation spans over 40000 generations per model across domains such as news, email, forums, and blogs, covering writing samples from more than 400 real-world authors. Results show that while LLMs can approximate user styles in structured formats like news and email, they struggle with nuanced, informal writing in blogs and forums. Further analysis on various prompting strategies such as number of demonstrations reveal key limitations in effective personalization. Our findings highlight a fundamental gap in personalized LLM adaptation and the need for improved techniques to support implicit, style-consistent generation. To aid future research and for reproducibility, we open-source our data and code.

Capturing professionals' decision-making in creative workflows is essential for reflection, collaboration, and knowledge sharing, yet existing methods often leave rationales incomplete and implicit decisions hidden. To address this, we present CLEAR framework that structures reasoning into cognitive decision steps-linked units of actions, artifacts, and self-explanations that make decisions traceable. Building on this framework, we introduce ClearFairy, a think-aloud AI assistant for UI design that detects weak explanations, asks lightweight clarifying questions, and infers missing rationales to ease the knowledge-sharing burden. In a study with twelve creative professionals, 85% of ClearFairy's inferred rationales were accepted, increasing strong explanations from 14% to over 83% of decision steps without adding cognitive demand. The captured steps also enhanced generative AI agents in Figma, yielding next-action predictions better aligned with professionals and producing more coherent design outcomes. For future research on human knowledge-grounded creative AI agents, we release a dataset of captured 417 decision steps.

Predictive process monitoring techniques support the operational decision-making by predicting future states of ongoing cases of a business process. A subset of these techniques predict the remaining sequence of activities of an ongoing case (case suffix prediction). Existing approaches for case suffix prediction generate sequences of activities with a single timestamp (e.g. the end timestamp). This output is insufficient for resource capacity planning, where we need to reason about the periods of time when resources will be busy performing work. This paper introduces a technique for predicting case suffixes consisting of activities with start and end timestamps. In other words, the proposed technique predicts both the waiting time and the processing time of each activity. Since the waiting time of an activity in a case depends on how busy resources are in other cases, the technique adopts a sweep-line approach, wherein the suffixes of all ongoing cases in the process are predicted in lockstep, rather than predictions being made for each case in isolation. An evaluation on real-life and synthetic datasets compares the accuracy of different instantiations of this approach, demonstrating the advantages of a multi-model approach to case suffix prediction.

Artificial Intelligence (AI) has transitioned from a futuristic concept reserved for large corporations to a present-day, accessible, and essential growth lever for Small and Medium-sized Enterprises (SMEs). For entrepreneurs and business leaders, strategic AI adoption is no longer an option but an imperative for competitiveness, operational efficiency, and long-term survival. This report provides a comprehensive framework for SME leaders to navigate this technological shift, offering the foundational knowledge, business case, practical applications, and strategic guidance necessary to harness the power of AI. The quantitative evidence supporting AI adoption is compelling; 91% of SMEs using AI report that it directly boosts their revenue. Beyond top-line growth, AI drives profound operational efficiencies, with studies showing it can reduce operational costs by up to 30% and save businesses more than 20 hours of valuable time each month. This transformation is occurring within the context of a seismic economic shift; the global AI market is projected to surge from $233.46 Billion in 2024 to an astonishing $1.77 Trillion by 2032. This paper demystifies the core concepts of AI, presents a business case based on market data, details practical applications, and lays out a phased, actionable adoption strategy.

Recent advancements in multimodal large language models (MLLMs) have garnered significant attention, offering a promising pathway toward artificial general intelligence (AGI). Among the essential capabilities required for AGI, creativity has emerged as a critical trait for MLLMs, with association serving as its foundation. Association reflects a model' s ability to think creatively, making it vital to evaluate and understand. While several frameworks have been proposed to assess associative ability, they often overlook the inherent ambiguity in association tasks, which arises from the divergent nature of associations and undermines the reliability of evaluations. To address this issue, we decompose ambiguity into two types-internal ambiguity and external ambiguity-and introduce AssoCiAm, a benchmark designed to evaluate associative ability while circumventing the ambiguity through a hybrid computational method. We then conduct extensive experiments on MLLMs, revealing a strong positive correlation between cognition and association. Additionally, we observe that the presence of ambiguity in the evaluation process causes MLLMs' behavior to become more random-like. Finally, we validate the effectiveness of our method in ensuring more accurate and reliable evaluations. See Project Page for the data and codes.

Abstract--Unsupervised anomalous sound detection aims to detect unknown anomalous sounds by training a model using only normal audio data. Despite advancements in self-supervised methods, the issue of frequent false alarms when handling samples of the same type from different machines remains unresolved. This paper introduces a novel training technique called one-stage supervised contrastive learning (OS-SCL), which significantly addresses this problem by perturbing features in the embedding space and employing a one-stage noisy supervised contrastive learning approach. On the DCASE 2020 Challenge T ask 2, it achieved 94.64% AUC, 88.42% pAUC, and 89.24% mAUC using only Log-Mel features. Additionally, a time-frequency feature named TFgram is proposed, which is extracted from raw audio.

This paper discusses our exploration of different data-efficient and parameter-efficient approaches to Arabic Dialect Identification (ADI). In particular, we investigate various soft-prompting strategies, including prefix-tuning, prompt-tuning, P-tuning, and P-tuning V2, as well as LoRA reparameterizations. For the data-efficient strategy, we analyze hard prompting with zero-shot and few-shot inferences to analyze the dialect identification capabilities of Large Language Models (LLMs). For the parameter-efficient PEFT approaches, we conducted our experiments using Arabic-specific encoder models on several major datasets. We also analyzed the n-shot inferences on open-source decoder-only models, a general multilingual model (Phi-3.5), and an Arabic-specific one(SILMA). We observed that the LLMs generally struggle to differentiate the dialectal nuances in the few-shot or zero-shot setups. The soft-prompted encoder variants perform better, while the LoRA-based fine-tuned models perform best, even surpassing full fine-tuning.

Large language models (LLMs) have achieved remarkable success in many natural language processing (NLP) tasks. To achieve more accurate output, the prompts used to drive LLMs have become increasingly longer, which incurs higher computational costs. To address this prompt inflation problem, prompt compression has been proposed. However, most existing methods require training a small auxiliary model for compression, incurring a significant amount of additional computation. To avoid this, we propose a two-stage, training-free approach, called Dual-Stage Progressive Compression (DSPC). In the coarse-grained stage, semantic-related sentence filtering removes sentences with low semantic value based on TF-IDF. In the fine-grained stage, token importance is assessed using attention contribution, cross-model loss difference, and positional importance, enabling the pruning of low-utility tokens while preserving semantics. We validate DSPC on LLaMA-3.1-8B-Instruct and GPT-3.5-Turbo under a constrained token budget and observe consistent improvements. For instance, in the FewShot task of the Longbench dataset, DSPC achieves a performance of 49.17 by using only 3x fewer tokens, outperforming the best state-of-the-art baseline LongLLMLingua by 7.76.

Social scientists are now using large language models to create " silicon samples" - synthetic datasets intended to stand in for human respondents, aimed at revolutionising human subjects research. However, there are many analytic choices which must be made to produce these samples. Though many of these choices are defen sible, their impact on sample quality is poorly understood . I map out these analytic choices and demonstrate how a very small number of decisions can dramatically change the correspondence between silicon samples and human data. Configurations (N = 252) varied substantially in their capacity to estimate (i) rank ordering of participants, (ii) response distributions, and (iii) between - scale correlations. Most critically, configurations were not consistent in quality: those that performed well on one dimension often performed poorly on another, implying that there i s no "one - size - fits - all" configuration that optimises the accuracy of these samples. I call for greater attention to the threat of analytic flexibility in using silicon samples. Generative large language models (LLMs) have ushered in a sea change within the social sciences. The capacity of these models to produce sensical natural language output to queries, as well as their flexibility, efficiency, and generalisability, has led re searchers to explore their use in tasks across the research process. One of the most ambitious proposed uses of LLMs in this respect has been to use them as simulated research participants to determine how human participants might respond to a particular context, set of survey questions, or intervention (Cui et al., 2025). This is based on the tacit assumption that, on some level, the corpuses of data which LLMs are trained on may enable them to approximate similar data - generating processes to those which underpin human responses (Z. If achievable, this could have a transformative impact on the social sciences.

ABSTRACT With the rapid progress of large audio-language models (LALMs), audio question answering (AQA) has emerged as a challenging task requiring both fine-grained audio understanding and complex reasoning. While current methods mainly rely on constructing new datasets via captioning or reasoning traces, existing high-quality AQA data remains underutilized. To address this, we propose Omni-CLST, an error-aware Curriculum Learning framework with guided Selective Chain-of-Thought. The framework efficiently leverages existing high-quality dataset through two key strategies: an error-aware curriculum that organizes samples by difficulty, and a guided thought dropout mechanism that focuses reasoning on challenging cases. Experiments show that Omni-CLST achieves 73.80% on MMAU-mini and a new state of the art of 64.30% on MMAR, demonstrating robust generalization in multimodal audio-language understanding.