With the rapid expansion of web-based applications and cloud services, malicious JavaScript code continues to pose significant threats to user privacy, system integrity, and enterprise security. But, detecting such threats remains challenging due to sophisticated code obfuscation techniques and JavaScript's inherent language characteristics, particularly its nested closure structures and syntactic flexibility. In this work, we propose DeCoda, a hybrid defense framework that combines large language model (LLM)-based deobfuscation with code graph learning: (1) We first construct a sophisticated prompt-learning pipeline with multi-stage refinement, where the LLM progressively reconstructs the original code structure from obfuscated inputs and then generates normalized Abstract Syntax Tree (AST) representations; (2) In JavaScript ASTs, dynamic typing scatters semantically similar nodes while deeply nested functions fracture scope capturing, introducing structural noise and semantic ambiguity. To address these challenges, we then propose to learn hierarchical code graph representations via a Cluster-wise Graph that synergistically integrates graph transformer network, node clustering, and node-to-cluster attention to simultaneously capture both local node-level semantics and global cluster-induced structural relationships from AST graph. Experimental results demonstrate that our method achieves F1-scores of 94.64% and 97.71% on two benchmark datasets, demonstrating absolute improvements of 10.74% and 13.85% over state-of-the-art baselines. In false-positive control evaluation at fixed FPR levels (0.0001, 0.001, 0.01), our approach delivers 4.82, 5.91, and 2.53 higher TPR respectively compared to the best-performing baseline. These results highlight the effectiveness of LLM-based deobfuscation and underscore the importance of modeling cluster-level relationships in detecting malicious code.

Can a language model trained largely on Anglo-American texts generate stories that are culturally relevant to other nationalities? To find out, we generated 11,800 stories - 50 for each of 236 countries - by sending the prompt "Write a 1500 word potential {demonym} story" to OpenAI's model gpt-4o-mini. Although the stories do include surface-level national symbols and themes, they overwhelmingly conform to a single narrative plot structure across countries: a protagonist lives in or returns home to a small town and resolves a minor conflict by reconnecting with tradition and organising community events. Real-world conflicts are sanitised, romance is almost absent, and narrative tension is downplayed in favour of nostalgia and reconciliation. The result is a narrative homogenisation: an AI-generated synthetic imaginary that prioritises stability above change and tradition above growth. We argue that the structural homogeneity of AI-generated narratives constitutes a distinct form of AI bias, a narrative standardisation that should be acknowledged alongside the more familiar representational bias. These findings are relevant to literary studies, narratology, critical AI studies, NLP research, and efforts to improve the cultural alignment of generative AI.

Large language models (LLMs) have emerged as transformative approaches in several important fields. This paper aims for a paradigm shift for patent writing by leveraging LLMs to overcome the tedious patent-filing process. In this work, we present PATENTWRITER, the first unified benchmarking framework for evaluating LLMs in patent abstract generation. Given the first claim of a patent, we evaluate six leading LLMs -- including GPT-4 and LLaMA-3 -- under a consistent setup spanning zero-shot, few-shot, and chain-of-thought prompting strategies to generate the abstract of the patent. Our benchmark PATENTWRITER goes beyond surface-level evaluation: we systematically assess the output quality using a comprehensive suite of metrics -- standard NLP measures (e.g., BLEU, ROUGE, BERTScore), robustness under three types of input perturbations, and applicability in two downstream patent classification and retrieval tasks. We also conduct stylistic analysis to assess length, readability, and tone. Experimental results show that modern LLMs can generate high-fidelity and stylistically appropriate patent abstracts, often surpassing domain-specific baselines. Our code and dataset are open-sourced to support reproducibility and future research.

--With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitations: 1) Static analysis methods struggle with complex scenarios. In contrast, general-purpose Large Language Models (LLMs) demonstrate impressive ability in adapting to new vulnerability patterns. However, they often underperform on specific vulnerability types compared to methods based on specialized pre-trained models. We also observe that explanations generated by general-purpose LLMs can provide fine-grained code understanding information, contributing to improved detection performance. Inspired by these observations, we propose SAEL, a LLMbased framework for smart contract vulnerability detection. First, we design prompts targeting specific smart contract vulnerabilities to guide general-purpose LLMs in detecting vulnerabilities and providing explanations. The detection results generated by LLMs serve as prediction features. Then, we employ prompt-tuning on CodeT5 and T5 respectively to process contract code and explanations, enhancing model performance on specific tasks. T o leverage the strengths of each component, we introduce Adaptive Mixture-of-Experts, a dynamic architecture for smart contract vulnerability detection. This mechanism dynamically adjusts feature weights through a Gating Network, which selects the most relevant features by applying T opK filtering and Softmax normalization, and a Multi-Head Self-Attention mechanism, which enhances cross-feature relationships by processing multiple attention heads in parallel. This design ensures that prediction results for LLMs, explanation features, and contract code features are effectively integrated through gradient optimization. The loss function focuses on the independent prediction performance of each feature and the overall performance of weighted predictions.

Accurate and reliable personality assessment plays a vital role in many fields, such as emotional intelligence, mental health diagnostics, and personalized education. Unlike fleeting emotions, personality traits are stable, often subconsciously leaked through language, facial expressions, and body behaviors, with asynchronous patterns across modalities. It was hard to model personality semantics with traditional superficial features and seemed impossible to achieve effective cross-modal understanding. To address these challenges, we propose a novel personality assessment framework called \textit{\textbf{Traits Run Deep}}. It employs \textit{\textbf{psychology-informed prompts}} to elicit high-level personality-relevant semantic representations. Besides, it devises a \textit{\textbf{Text-Centric Trait Fusion Network}} that anchors rich text semantics to align and integrate asynchronous signals from other modalities. To be specific, such fusion module includes a Chunk-Wise Projector to decrease dimensionality, a Cross-Modal Connector and a Text Feature Enhancer for effective modality fusion and an ensemble regression head to improve generalization in data-scarce situations. To our knowledge, we are the first to apply personality-specific prompts to guide large language models (LLMs) in extracting personality-aware semantics for improved representation quality. Furthermore, extracting and fusing audio-visual apparent behavior features further improves the accuracy. Experimental results on the AVI validation set have demonstrated the effectiveness of the proposed components, i.e., approximately a 45\% reduction in mean squared error (MSE). Final evaluations on the test set of the AVI Challenge 2025 confirm our method's superiority, ranking first in the Personality Assessment track. The source code will be made available at https://github.com/MSA-LMC/TraitsRunDeep.

--Metaverse service is a product of the convergence between Metaverse and service systems, designed to address service-related challenges concerning digital avatars, digital twins, and digital natives within Metaverse. With the rise of large language models (LLMs), agents now play a pivotal role in Metaverse service ecosystem, serving dual functions: as digital avatars representing users in the virtual realm and as service assistants (or NPCs) providing personalized support. However, during the modeling of Metaverse service ecosystems, existing LLMbased agents face significant challenges in bridging virtual-world services with real-world services, particularly regarding issues such as character data fusion, character knowledge association, and ethical safety concerns. This paper proposes an explainable emotion alignment framework for LLM-based agents in Meta-verse Service Ecosystem. It aims to integrate factual factors into the decision-making loop of LLM-based agents, systematically demonstrating how to achieve more relational fact alignment for these agents. Finally, a simulation experiment in the Offline-to-Offline food delivery scenario is conducted to evaluate the effectiveness of this framework, obtaining more realistic social emergence. Serving as its operational core, services support interactions among humans, objects, and scenarios within this virtual space. As an emerging service paradigm, Metaverse services integrate multi-source heterogeneous digital resources to establish collaborative mechanisms across networks, domains, and spaces, effectively addressing service requirements for digital avatars, digital twins, and digital natives [1].

We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a cost-efficient way to estimate the quality of data sources (e.g. synthetically generated or filtered web data, etc.) in order to make optimal decisions about resource allocation for data sourcing from these sources for the stage two pre-training phase, aka annealing, with the goal of specializing a generalist pre-trained model to specific domains. Our approach extends the usual point estimate approaches, aka micro-annealing, to estimating scaling laws by performing multiple annealing runs of varying compute spent on data curation and training. This addresses a key limitation in prior work, where reliance on point estimates for data scaling decisions can be misleading due to the lack of rank invariance across compute scales -- a phenomenon we confirm in our experiments. By systematically analyzing performance gains relative to acquisition costs, we find that scaling curves can be estimated for different data sources. Such scaling laws can inform cost effective resource allocation across different data acquisition methods (e.g. synthetic data), data sources (e.g. user or web data) and available compute resources. We validate our approach through experiments on a pre-trained model with 7 billion parameters. We adapt it to: a domain well-represented in the pre-training data -- the medical domain, and a domain underrepresented in the pretraining corpora -- the math domain. We show that one can efficiently estimate the scaling behaviors of a data source by running multiple annealing runs, which can lead to different conclusions, had one used point estimates using the usual micro-annealing technique instead. This enables data-driven decision-making for selecting and optimizing data sources.

Remote fetal monitoring technologies are becoming increasingly common. Yet, most current systems offer limited interpretability, leaving expectant parents with raw cardiotocography (CTG) data that is difficult to understand. In this work, we present CTG-Insight, a multi-agent LLM system that provides structured interpretations of fetal heart rate (FHR) and uterine contraction (UC) signals. Drawing from established medical guidelines, CTG-Insight decomposes each CTG trace into five medically defined features: baseline, variability, accelerations, decelerations, and sinusoidal pattern, each analyzed by a dedicated agent. A final aggregation agent synthesizes the outputs to deliver a holistic classification of fetal health, accompanied by a natural language explanation. We evaluate CTG-Insight on the NeuroFetalNet Dataset and compare it against deep learning models and the single-agent LLM baseline. Results show that CTG-Insight achieves state-of-the-art accuracy (96.4%) and F1-score (97.8%) while producing transparent and interpretable outputs. This work contributes an interpretable and extensible CTG analysis framework.

This paper argues that explainability is only one facet of a broader ideal that shapes our expectations towards artificial intelligence (AI). Fundamentally, the issue is to what extent AI exhibits systematicity--not merely in being sensitive to how thoughts are composed of recombinable constituents, but in striving towards an integrated body of thought that is consistent, coherent, comprehensive, and parsimoniously principled. This richer conception of systematicity has been obscured by the long shadow of the "systematicity challenge" to connectionism, according to which network architectures are fundamentally at odds with what Fodor and colleagues termed "the systematicity of thought." I offer a conceptual framework for thinking about "the systematicity of thought" that distinguishes four senses of the phrase. I use these distinctions to defuse the perceived tension between systematicity and connectionism and show that the conception of systematicity that historically shaped our sense of what makes thought rational, authoritative, and scientific is more demanding than the Fodorian notion. To determine whether we have reason to hold AI models to this ideal of systematicity, I then argue, we must look to the rationales for systematization and explore to what extent they transfer to AI models. I identify five such rationales and apply them to AI. This brings into view the "hard systematicity challenge." However, the demand for systematization itself needs to be regulated by the rationales for systematization. This yields a dynamic understanding of the need to systematize thought, which tells us how systematic we need AI models to be and when.

We present an automated pipeline for estimating Verb Frame Frequencies (VFFs), the frequency with which a verb appears in particular syntactic frames. VFFs provide a powerful window into syntax in both human and machine language systems, but existing tools for calculating them are limited in scale, accuracy, or accessibility. We use large language models (LLMs) to generate a corpus of sentences containing 476 English verbs. Next, by instructing an LLM to behave like an expert linguist, we had it analyze the syntactic structure of the sentences in this corpus. This pipeline outperforms two widely used syntactic parsers across multiple evaluation datasets. Furthermore, it requires far fewer resources than manual parsing (the gold-standard), thereby enabling rapid, scalable VFF estimation. Using the LLM parser, we produce a new VFF database with broader verb coverage, finer-grained syntactic distinctions, and explicit estimates of the relative frequencies of structural alternates commonly studied in psycholinguistics. The pipeline is easily customizable and extensible to new verbs, syntactic frames, and even other languages. We present this work as a proof of concept for automated frame frequency estimation, and release all code and data to support future research.