Toxic comment detection remains a challenging task, where transformer-based models (e.g., BERT) incur high computational costs and degrade on minority toxicity classes, while classical ensembles lack semantic adaptability. We propose xLSTM, a parameter-efficient and theoretically grounded framework that unifies cosine-similarity gating, adaptive feature prioritization, and principled class rebalancing. A learnable reference vector {v} in {R}^d modulates contextual embeddings via cosine similarity, amplifying toxic cues and attenuating benign signals to yield stronger gradients under severe class imbalance. xLSTM integrates multi-source embeddings (GloVe, FastText, BERT CLS) through a projection layer, a character-level BiLSTM for morphological cues, embedding-space SMOTE for minority augmentation, and adaptive focal loss with dynamic class weighting. On the Jigsaw Toxic Comment benchmark, xLSTM attains 96.0% accuracy and 0.88 macro-F1, outperforming BERT by 33% on threat and 28% on identity_hate categories, with 15 times fewer parameters and 50ms inference latency. Cosine gating contributes a +4.8% F1 gain in ablations. The results establish a new efficiency adaptability frontier, demonstrating that lightweight, theoretically informed architectures can surpass large pretrained models on imbalanced, domain-specific NLP tasks.

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely on single-label benchmarks, which cannot adequately capture the inherently ambiguous and multi-dimensional nature of real-world toxic prompts. This limitation results in biased evaluations, including missed toxic detections and false positives, undermining the reliability of existing detectors. Additionally, gathering comprehensive multi-label annotations across fine-grained toxicity categories is prohibitively costly, further hindering effective evaluation and development. To tackle these issues, we introduce three novel multi-label benchmarks for toxicity detection: \textbf{Q-A-MLL}, \textbf{R-A-MLL}, and \textbf{H-X-MLL}, derived from public toxicity datasets and annotated according to a detailed 15-category taxonomy. We further provide a theoretical proof that, on our released datasets, training with pseudo-labels yields better performance than directly learning from single-label supervision. In addition, we develop a pseudo-label-based toxicity detection method. Extensive experimental results show that our approach significantly surpasses advanced baselines, including GPT-4o and DeepSeek, thus enabling more accurate and reliable evaluation of multi-label toxicity in LLM-generated content.

We draw inspiration from microsaccades, tiny involuntary eye movements that reveal hidden dynamics of human perception, to propose an analogous probing method for large language models (LLMs). Just as microsaccades expose subtle but informative shifts in vision, we show that lightweight position encoding perturbations elicit latent signals that indicate model misbehaviour. Our method requires no fine-tuning or task-specific supervision, yet detects failures across diverse settings including factuality, safety, toxicity, and backdoor attacks. Experiments on multiple state-of-the-art LLMs demonstrate that these perturbation-based probes surface misbehaviours while remaining computationally efficient. These findings suggest that pretrained LLMs already encode the internal evidence needed to flag their own failures, and that microsaccade-inspired interventions provide a pathway for detecting and mitigating undesirable behaviours.

The evolution of digital communication systems and the designs of online platforms have inadvertently facilitated the subconscious propagation of toxic behavior. Giving rise to reactive responses to toxic behavior. Toxicity in online content and Artificial Intelligence Systems has become a serious challenge to individual and collective well-being around the world. It is more detrimental to society than we realize. Toxicity, expressed in language, image, and video, can be interpreted in various ways depending on the context of usage. Therefore, a comprehensive taxonomy is crucial to detect and mitigate toxicity in online content, Artificial Intelligence systems, and/or Large Language Models in a proactive manner. A comprehensive understanding of toxicity is likely to facilitate the design of practical solutions for toxicity detection and mitigation. The classification in published literature has focused on only a limited number of aspects of this very complex issue, with a pattern of reactive strategies in response to toxicity. This survey attempts to generate a comprehensive taxonomy of toxicity from various perspectives. It presents a holistic approach to explain the toxicity by understanding the context and environment that society is facing in the Artificial Intelligence era. This survey summarizes the toxicity-related datasets and research on toxicity detection and mitigation for Large Language Models, social media platforms, and other online platforms, detailing their attributes in textual mode, focused on the English language. Finally, we suggest the research gaps in toxicity mitigation based on datasets, mitigation strategies, Large Language Models, adaptability, explainability, and evaluation.

Most languages lack sufficient data for large-scale monolingual pretraining, creating a "data wall." Multilingual pretraining helps but is limited by language imbalance and the "curse of multilinguality." An alternative is to translate high-resource text with machine translation (MT), which raises three questions: (1) How does MT-derived data scale with model capacity? (2) Can source-side transformations (e.g., simplifying English with an LLM) improve generalization to native text? (3) How well do models pretrained on MT-derived data adapt when continually trained on limited native text? We investigate these questions by translating English into Indonesian and Tamil--two typologically distant, lower-resource languages--and pretraining GPT-2 models (124M-774M) on native or MT-derived corpora from raw and LLM-simplified English. We evaluate cross-entropy loss on native text, along with accuracy on syntactic probes and downstream tasks. Our results show that (1) MT-pretrained models benefit from scaling; (2) source-side simplification harms generalization to native text; and (3) adapting MT-pretrained models on native text often yields better performance than native-only models, even with less native data. However, tasks requiring cultural nuance (e.g., toxicity detection) demand more exposure to native data.

Large Language Models have demonstrated impressive fluency across diverse tasks, yet their tendency to produce toxic content remains a critical challenge for AI safety and public trust. Existing toxicity mitigation approaches primarily manipulate individual neuron activations, but these methods suffer from instability, context dependence, and often compromise the model's core language abilities. To address these shortcomings, we investigate three key questions: the stability of neuron-level toxicity indicators, the advantages of structural (layer-wise) representations, and the interpretability of mechanisms driving toxic generation. Through extensive experiments on Jigsaw and ToxiCN datasets, we show that aggregated layer-wise features provide more robust signals than single neurons. Moreover, we observe conceptual limitations in prior works that conflate toxicity detection experts and generation experts within neuron-based interventions. To mitigate this, we propose a novel principled intervention technique, EigenShift, based on eigen-decomposition of the language model's final output layer. This method selectively targets generation-aligned components, enabling precise toxicity suppression without impairing linguistic competence. Our method requires no additional training or fine-tuning, incurs minimal computational cost, and is grounded in rigorous theoretical analysis.

Multilingual toxicity detection remains a significant challenge due to the scarcity of training data and resources for many languages. While prior work has leveraged the translate-test paradigm to support cross-lingual transfer across a range of classification tasks, the utility of translation in supporting toxicity detection at scale remains unclear. In this work, we conduct a comprehensive comparison of translation-based and language-specific/multilingual classification pipelines. We find that translation-based pipelines consistently outperform out-of-distribution classifiers in 81.3% of cases (13 of 16 languages), with translation benefits strongly correlated with both the resource level of the target language and the quality of the machine translation (MT) system. Our analysis reveals that traditional classifiers outperform large language model (LLM) judges, with this advantage being particularly pronounced for low-resource languages, where translate-classify methods dominate translate-judge approaches in 6 out of 7 cases. We additionally show that MT-specific fine-tuning on LLMs yields lower refusal rates compared to standard instruction-tuned models, but it can negatively impact toxicity detection accuracy for low-resource languages. These findings offer actionable guidance for practitioners developing scalable multilingual content moderation systems.

In the digital era, individuals are increasingly exposed to online harms such as toxicity, manipulation, and grooming, which often pose emotional and safety risks. Existing systems for detecting abusive content or issuing safety alerts operate in isolation and rarely combine digital safety with emotional well-being. In this paper, we present SafeSpace, a unified web application that integrates three modules: (1) toxicity detection in chats and screenshots using NLP models and Google's Perspective API, (2) a configurable safety ping system that issues emergency alerts with the user's live location (longitude and latitude) via SMTP-based emails when check-ins are missed or SOS alerts are manually triggered, and (3) a reflective questionnaire that evaluates relationship health and emotional resilience. The system employs Firebase for alert management and a modular architecture designed for usability, privacy, and scalability. The experimental evaluation shows 93% precision in toxicity detection, 100% reliability in safety alerts under emulator tests, and 92% alignment between automated and manual questionnaire scoring. SafeSpace, implemented as a web application, demonstrates the feasibility of integrating detection, protection, and reflection within a single platform, with future deployment envisioned as a mobile application for broader accessibility.

Risk perception is subjective, and youth's understanding of toxic content differs from that of adults. Although previous research has conducted extensive studies on toxicity detection in social media, the investigation of youth's unique toxicity, i.e., languages perceived as nontoxic by adults but toxic as youth, is ignored. To address this gap, we aim to explore: 1) What are the features of ``youth-toxicity'' languages in social media (RQ1); 2) Can existing toxicity detection techniques accurately detect these languages (RQ2). For these questions, we took Chinese youth as the research target, constructed the first Chinese ``youth-toxicity'' dataset, and then conducted extensive analysis. Our results suggest that youth's perception of these is associated with several contextual factors, like the source of an utterance and text-related features. Incorporating these meta information into current toxicity detection methods significantly improves accuracy overall. Finally, we propose several insights into future research on youth-centered toxicity detection.