Frontier language model quality increasingly hinges on our ability to organize web-scale text corpora for training. Today's dominant tools trade off speed and flexibility: lexical classifiers (e.g., FastText) are fast but limited to producing classification output scores, while the vector-valued outputs of transformer text embedding models flexibly support numerous workflows (e.g., clustering, classification, and retrieval) but are computationally expensive to produce. We introduce Luxical, a library for high-speed "lexical-dense" text embeddings that aims to recover the best properties of both approaches for web-scale text organization. Luxical combines sparse TF--IDF features, a small ReLU network, and a knowledge distillation training regimen to approximate large transformer embedding models at a fraction of their operational cost. In this technical report, we describe the Luxical architecture and training objective and evaluate a concrete Luxical model in two disparate applications: a targeted webcrawl document retrieval test and an end-to-end language model data curation task grounded in text classification. In these tasks we demonstrate speedups ranging from 3x to 100x over varying-sized neural baselines, and comparable to FastText model inference during the data curation task. On these evaluations, the tested Luxical model illustrates favorable compute/quality trade-offs for large-scale text organization, matching the quality of neural baselines. Luxical is available as open-source software at this https URL.

Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with gradient search or rule-based methods, but these are brittle and often tied to a single task or model. In this paper, a reinforcement learning framework is used where the suffix is treated as a policy and trained with Proximal Policy Optimization against a frozen model as a reward oracle. Rewards are shaped using calibrated cross-entropy, removing label bias and aggregating across surface forms to improve transferability. The proposed method is evaluated on five diverse NLP benchmark datasets, covering sentiment, natural language inference, paraphrase, and commonsense reasoning, using three distinct language models: Qwen2-1.5B Instruct, TinyLlama-1.1B Chat, and Phi-1.5. Results show that RL-trained suffixes consistently degrade accuracy and transfer more effectively across tasks and models than previous adversarial triggers of similar genres.

Understanding human personality is crucial for web applications such as personalized recommendation and mental health assessment. Existing studies on personality detection predominantly adopt a "posts -> user vector -> labels" modeling paradigm, which encodes social media posts into user representations for predicting personality labels (e.g., MBTI labels). While recent advances in large language models (LLMs) have improved text encoding capacities, these approaches remain constrained by limited supervision signals due to label scarcity, and under-specified semantic mappings between user language and abstract psychological constructs. We address these challenges by proposing ROME, a novel framework that explicitly injects psychological knowledge into personality detection. Inspired by standardized self-assessment tests, ROME leverages LLMs' role-play capability to simulate user responses to validated psychometric questionnaires. These generated question-level answers transform free-form user posts into interpretable, questionnaire-grounded evidence linking linguistic cues to personality labels, thereby providing rich intermediate supervision to mitigate label scarcity while offering a semantic reasoning chain that guides and simplifies the text-to-personality mapping learning. A question-conditioned Mixture-of-Experts module then jointly routes over post and question representations, learning to answer questionnaire items under explicit supervision. The predicted answers are summarized into an interpretable answer vector and fused with the user representation for final prediction within a multi-task learning framework, where question answering serves as a powerful auxiliary task for personality detection. Extensive experiments on two real-world datasets demonstrate that ROME consistently outperforms state-of-the-art baselines, achieving improvements (15.41% on Kaggle dataset).

The proliferation of hate speech on Chinese social media poses urgent societal risks, yet traditional systems struggle to decode context-dependent rhetorical strategies and evolving slang. To bridge this gap, we propose a novel three-stage LLM-based framework: Prompt Engineering, Supervised Fine-tuning, and LLM Merging. First, context-aware prompts are designed to guide LLMs in extracting implicit hate patterns. Next, task-specific features are integrated during supervised fine-tuning to enhance domain adaptation. Finally, merging fine-tuned LLMs improves robustness against out-of-distribution cases. Evaluations on the STATE-ToxiCN benchmark validate the framework's effectiveness, demonstrating superior performance over baseline methods in detecting fine-grained hate speech.

Modern businesses are increasingly challenged by the time and expense required to generate and assess high-quality content. Human writers face time constraints, and extrinsic evaluations can be costly. While Large Language Models (LLMs) offer potential in content creation, concerns about the quality of AI-generated content persist. Traditional evaluation methods, like human surveys, further add operational costs, highlighting the need for efficient, automated solutions. This research introduces Generative Agents as a means to tackle these challenges. These agents can rapidly and cost-effectively evaluate AI-generated content, simulating human judgment by rating aspects such as coherence, interestingness, clarity, fairness, and relevance. By incorporating these agents, businesses can streamline content generation and ensure consistent, high-quality output while minimizing reliance on costly human evaluations. The study provides critical insights into enhancing LLMs for producing business-aligned, high-quality content, offering significant advancements in automated content generation and evaluation.

Interpreto is a Python library for post-hoc explainability of text HuggingFace models, from early BERT variants to LLMs. It provides two complementary families of methods: attributions and concept-based explanations. The library connects recent research to practical tooling for data scientists, aiming to make explanations accessible to end users. It includes documentation, examples, and tutorials. Interpreto supports both classification and generation models through a unified API. A key differentiator is its concept-based functionality, which goes beyond feature-level attributions and is uncommon in existing libraries. The library is open source; install via pip install interpreto. Code and documentation are available at this https URL.

Sensitive information leakage in code repositories has emerged as a critical security challenge. Traditional detection methods that rely on regular expressions, fingerprint features, and high-entropy calculations often suffer from high false-positive rates. This not only reduces detection efficiency but also significantly increases the manual screening burden on developers. Recent advances in large language models (LLMs) and multi-agent collaborative architectures have demonstrated remarkable potential for tackling complex tasks, offering a novel technological perspective for sensitive information detection. In response to these challenges, we propose Argus, a multi-agent collaborative framework for detecting sensitive information. Argus employs a three-tier detection mechanism that integrates key content, file context, and project reference relationships to effectively reduce false positives and enhance overall detection accuracy. To comprehensively evaluate Argus in real-world repository environments, we developed two new benchmarks, one to assess genuine leak detection capabilities and another to evaluate false-positive filtering performance. Experimental results show that Argus achieves up to 94.86% accuracy in leak detection, with a precision of 96.36%, recall of 94.64%, and an F1 score of 0.955. Moreover, the analysis of 97 real repositories incurred a total cost of only 2.2$. All code implementations and related datasets are publicly available at this https URL for further research and application.

This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings from audio with text is the large length of the audio sequence compared to the text one. Our method benefits from an existing speech tokenizer trained for Audio Speech Recognition that output long sequences of tokens from a large vocabulary, making it difficult to integrate it at low cost in a large language model. By applying a simple lasso-based feature selection on multimodal Bag-of-Words representation, we retain only the most important audio tokens for the task, and adapt the language model to them with a self-supervised language modeling objective, before fine-tuning it on the downstream task. We show this helps to improve the performances compared to an unimodal model, to a bigger SpeechLM or to integrating audio via a learned representation. We show the effectiveness of our method on two recent Argumentative Fallacy Detection and Classification tasks where the use of audio was believed counterproductive, reaching state-of-the-art results. We also provide an in-depth analysis of the method, showing that even a random audio token selection helps enhancing the unimodal model. Our code is available [online](this https URL).

This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class imbalance. The framework includes text encoding, contextual representation modeling, attention-based enhancement, feature aggregation, and classification prediction. In the representation stage, deep semantic embeddings are obtained through large-scale pretrained language models, and attention mechanisms are applied to enhance the selective representation of key features. In the aggregation stage, global and weighted strategies are combined to generate robust text-level vectors. In the classification stage, a fully connected layer and Softmax output are used to predict class distributions, and cross-entropy loss is employed to optimize model parameters. Comparative experiments introduce multiple baseline models, including recurrent neural networks, graph neural networks, and Transformers, and evaluate them on Precision, Recall, F1-Score, and AUC. Results show that the proposed method outperforms existing models on all metrics, with especially strong improvements in Recall and AUC. In addition, sensitivity experiments are conducted on hyperparameters and data conditions, covering the impact of hidden dimensions on AUC and the impact of class imbalance ratios on Recall. The findings demonstrate that proper model configuration has a significant effect on performance and reveal the adaptability and stability of the model under different conditions. Overall, the proposed text classification method not only achieves effective performance improvement but also verifies its robustness and applicability in complex data environments through systematic analysis.

This paper investigates bias in GLLM annotations by conceptually replicating manual annotations of Boukes (2024). Using various GLLMs (Llama3.1:8b, Llama3.3:70b, GPT4o, Qwen2.5:72b) in combination with five different prompts for five concepts (political content, interactivity, rationality, incivility, and ideology). We find GLLMs perform adequate in terms of F1 scores, but differ from manual annotations in terms of prevalence, yield substantively different downstream results, and display systematic bias in that they overlap more with each other than with manual annotations. Differences in F1 scores fail to account for the degree of bias.

We present FineFreq, a large-scale multilingual character frequency dataset derived from the FineWeb and FineWeb2 corpora, covering over 1900 languages and spanning 2013-2025. The dataset contains frequency counts for 96 trillion characters processed from 57 TB of compressed text. For each language, FineFreq provides per-character statistics with aggregate and year-level frequencies, allowing fine-grained temporal analysis. The dataset preserves naturally occurring multilingual features such as cross-script borrowings, emoji, and acronyms without applying artificial filtering. Each character entry includes Unicode metadata (category, script, block), enabling domain-specific or other downstream filtering and analysis. The full dataset is released in both CSV and Parquet formats, with associated metadata, available on GitHub and HuggingFace. this https URL

Language models (LMs) are often used as zero-shot or few-shot classifiers by scoring label words, but they remain fragile to adversarial prompts. Prior work typically optimizes task- or model-specific triggers, making results difficult to compare and limiting transferability. We study universal adversarial suffixes: short token sequences (4-10 tokens) that, when appended to any input, broadly reduce accuracy across tasks and models. Our approach learns the suffix in a differentiable "soft" form using Gumbel-Softmax relaxation and then discretizes it for inference. Training maximizes calibrated cross-entropy on the label region while masking gold tokens to prevent trivial leakage, with entropy regularization to avoid collapse. A single suffix trained on one model transfers effectively to others, consistently lowering both accuracy and calibrated confidence. Experiments on sentiment analysis, natural language inference, paraphrase detection, commonsense QA, and physical reasoning with Qwen2-1.5B, Phi-1.5, and TinyLlama-1.1B demonstrate consistent attack effectiveness and transfer across tasks and model families.

Text clustering is a fundamental task in natural language processing, yet traditional clustering algorithms with pre-trained embeddings often struggle in domain-specific contexts without costly fine-tuning. Large language models (LLMs) provide strong contextual reasoning, yet prior work mainly uses them as auxiliary modules to refine embeddings or adjust cluster boundaries. We propose ClusterFusion, a hybrid framework that instead treats the LLM as the clustering core, guided by lightweight embedding methods. The framework proceeds in three stages: embedding-guided subset partition, LLM-driven topic summarization, and LLM-based topic assignment. This design enables direct incorporation of domain knowledge and user preferences, fully leveraging the contextual adaptability of LLMs. Experiments on three public benchmarks and two new domain-specific datasets demonstrate that ClusterFusion not only achieves state-of-the-art performance on standard tasks but also delivers substantial gains in specialized domains. To support future work, we release our newly constructed dataset and results on all benchmarks.

This paper investigates the detection of misinformation, which deceives readers by explicitly fabricating misleading content or implicitly omitting important information necessary for informed judgment. While the former has been extensively studied, omission-based deception remains largely overlooked, even though it can subtly guide readers toward false conclusions under the illusion of completeness. To pioneer in this direction, this paper presents OmiGraph, the first omission-aware framework for misinformation detection. Specifically, OmiGraph constructs an omission-aware graph for the target news by utilizing a contextual environment that captures complementary perspectives of the same event, thereby surfacing potentially omitted contents. Based on this graph, omission-oriented relation modeling is then proposed to identify the internal contextual dependencies, as well as the dynamic omission intents, formulating a comprehensive omission relation representation. Finally, to extract omission patterns for detection, OmiGraph introduces omission-aware message-passing and aggregation that establishes holistic deception perception by integrating the omission contents and relations. Experiments show that, by considering the omission perspective, our approach attains remarkable performance, achieving average improvements of +5.4% F1 and +5.3% ACC on two large-scale benchmarks.

We present LOCUS (LOw-cost Customization for Universal Specialization), a pipeline that consumes few-shot data to streamline the construction and training of NLP models through targeted retrieval, synthetic data generation, and parameter-efficient tuning. With only a small number of labeled examples, LOCUS discovers pertinent data in a broad repository, synthesizes additional training samples via in-context data generation, and fine-tunes models using either full or low-rank (LoRA) parameter adaptation. Our approach targets named entity recognition (NER) and text classification (TC) benchmarks, consistently outperforming strong baselines (including GPT-4o) while substantially lowering costs and model sizes. Our resultant memory-optimized models retain 99% of fully fine-tuned accuracy while using barely 5% of the memory footprint, also beating GPT-4o on several benchmarks with less than 1% of its parameters.

Legal general intelligence (GI) refers to artificial intelligence (AI) that encompasses legal understanding, reasoning, and decision-making, simulating the expertise of legal experts across domains. However, existing benchmarks are result-oriented and fail to systematically evaluate the legal intelligence of large language models (LLMs), hindering the development of legal GI. To address this, we propose LexGenius, an expert-level Chinese legal benchmark for evaluating legal GI in LLMs. It follows a Dimension-Task-Ability framework, covering seven dimensions, eleven tasks, and twenty abilities. We use the recent legal cases and exam questions to create multiple-choice questions with a combination of manual and LLM reviews to reduce data leakage risks, ensuring accuracy and reliability through multiple rounds of checks. We evaluate 12 state-of-the-art LLMs using LexGenius and conduct an in-depth analysis. We find significant disparities across legal intelligence abilities for LLMs, with even the best LLMs lagging behind human legal professionals. We believe LexGenius can assess the legal intelligence abilities of LLMs and enhance legal GI development. Our project is available at this https URL.

The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate with their internal semantics undocumented or even intentionally withheld. Such opaque classifiers, which may expose only hard-label outputs, can operate in unregulated web environments or be repurposed for unknown intents, raising legitimate forensic and auditing concerns. In this paper, we position ourselves as investigators and work to infer the semantic concept each label encodes in an undocumented black-box classifier. Specifically, we introduce label forensics, a black-box framework that reconstructs a label's semantic meaning. Concretely, we represent a label by a sentence embedding distribution from which any sample reliably reflects the concept the classifier has implicitly learned for that label. We believe this distribution should maintain two key properties: precise, with samples consistently classified into the target label, and general, covering the label's broad semantic space. To realize this, we design a semantic neighborhood sampler and an iterative optimization procedure to select representative seed sentences that jointly maximize label consistency and distributional coverage. The final output, an optimized seed sentence set combined with the sampler, constitutes the empirical distribution representing the label's semantics. Experiments on multiple black-box classifiers achieve an average label consistency of around 92.24 percent, demonstrating that the embedding regions accurately capture each classifier's label semantics. We further validate our framework on an undocumented HuggingFace classifier, enabling fine-grained label interpretation and supporting responsible AI auditing.

The rapid proliferation of Large Language Models (LLMs) has blurred the line between human and machine authorship, creating practical risks for academic integrity and information reliability. Existing text detectors typically rely on a single methodological paradigm and suffer from poor generalization and high false positive rates (FPR), especially on high-stakes academic text. We propose a theoretically grounded hybrid ensemble that systematically fuses three complementary detection paradigms: (i) a RoBERTa-based transformer classifier for deep semantic feature extraction, (ii) a GPT-2-based probabilistic detector using perturbation-induced likelihood curvature, and (iii) a statistical linguistic feature analyzer capturing stylometric patterns. The core novelty lies in an optimized weighted voting framework, where ensemble weights are learned on the probability simplex to maximize F1-score rather than set heuristically. We provide a bias-variance analysis and empirically demonstrate low inter-model correlation (rho ~ 0.35-0.42), a key condition for variance reduction. Evaluated on a large-scale, multigenerator corpus of 30,000 documents, our system achieves 94.2% accuracy and an AUC of 0.978, with a 35% relative reduction in false positives on academic text. This yields a more reliable and ethically responsible detector for real-world deployment in education and other high-stakes domains.