Large language models (LLMs) are widely adopted to generate synthetic datasets for various natural language processing (NLP) tasks, such as text classification and summarization. However, accurately measuring the diversity of these synthetic datasets-an aspect crucial for robust model performance-remains a significant challenge. In this paper, we introduce DCScore, a novel method for measuring synthetic dataset diversity from a classification perspective. Specifically, DCScore formulates diversity evaluation as a sample classification task, leveraging mutual relationships among samples. We further provide theoretical verification of the diversity-related axioms satisfied by DCScore, highlighting its role as a principled diversity evaluation method. Experimental results on synthetic datasets reveal that DCScore enjoys a stronger correlation with multiple diversity pseudo-truths of evaluated datasets, underscoring its effectiveness. Moreover, both empirical and theoretical evidence demonstrate that DCScore substantially reduces computational costs compared to existing approaches. Code is available at: https://github.com/BlueWhaleLab/DCScore.
Interpreting the internal mechanisms of large language models (LLMs) is crucial for improving their trustworthiness and utility. Prior work has primarily focused on mapping individual neurons to discrete semantic concepts. However, such mappings struggle to handle the inherent polysemanticity in LLMs, where individual neurons encode multiple, distinct concepts. Through a comprehensive analysis of both encoder and decoder-based LLMs across diverse datasets, we observe that even highly salient neurons, identified via various attribution techniques for specific semantic concepts, consistently exhibit polysemantic behavior. Importantly, activation magnitudes for fine-grained concepts follow distinct, often Gaussian-like distributions with minimal overlap. This observation motivates a shift from neuron attribution to range-based interpretation. We hypothesize that interpreting and manipulating neuron activation ranges would enable more precise interpretability and targeted interventions in LLMs. To validate our hypothesis, we introduce NeuronLens, a novel range-based interpretation and manipulation framework that provides a finer view of neuron activation distributions to localize concept attribution within a neuron. Extensive empirical evaluations demonstrate that NeuronLens significantly reduces unintended interference, while maintaining precise manipulation of targeted concepts, outperforming neuron attribution.
We present PRINCIPLE-BASED PROMPTING, a simple but effective multi-agent prompting strategy for text classification. It first asks multiple LLM agents to independently generate candidate principles based on analysis of demonstration samples with or without labels, consolidates them into final principles via a finalizer agent, and then sends them to a classifier agent to perform downstream classification tasks. Extensive experiments on binary and multi-class classification datasets with different sizes of LLMs show that our approach not only achieves substantial performance gains (1.55% - 19.37%) over zero-shot prompting on macro-F1 score but also outperforms other strong baselines (CoT and stepback prompting). Principles generated by our approach help LLMs perform better on classification tasks than human crafted principles on two private datasets. Our multi-agent PRINCIPLE-BASED PROMPTING approach also shows on-par or better performance compared to demonstration-based few-shot prompting approaches, yet with substantially lower inference costs. Ablation studies show that label information and the multi-agent cooperative LLM framework play an important role in generating high-quality principles to facilitate downstream classification tasks.
Multilingual language models have significantly advanced due to rapid progress in natural language processing. Models like BLOOM 1.7B, trained on diverse multilingual datasets, aim to bridge linguistic gaps. However, their effectiveness in capturing linguistic knowledge, particularly for low-resource languages, remains an open question. This study critically examines MLMs capabilities in multilingual understanding, semantic representation, and cross-lingual knowledge transfer. While these models perform well for high-resource languages, they struggle with less-represented ones. Additionally, traditional evaluation methods often overlook their internal syntactic and semantic encoding. This research addresses key limitations through three objectives. First, it assesses semantic similarity by analyzing multilingual word embeddings for consistency using cosine similarity. Second, it examines BLOOM-1.7B and Qwen2 through Named Entity Recognition and sentence similarity tasks to understand their linguistic structures. Third, it explores cross-lingual knowledge transfer by evaluating generalization from high-resource to low-resource languages in sentiment analysis and text classification. By leveraging linguistic probing, performance metrics, and visualizations, this study provides insights into the strengths and limitations of MLMs. The findings aim to enhance multilingual NLP models, ensuring better support for both high- and low-resource languages, thereby promoting inclusivity in language technologies.
The automatic detection of disinformation presents a significant challenge in the field of natural language processing. This task addresses a multifaceted societal and communication issue, which needs approaches that extend beyond the identification of general linguistic patterns through data-driven algorithms. In this research work, we hypothesise that text classification methods are not able to capture the nuances of disinformation and they often ground their decision in superfluous features. Hence, we apply a post-hoc explainability method (SHAP, SHapley Additive exPlanations) to identify spurious elements with high impact on the classification models. Our findings show that non-informative elements (e.g., URLs and emoticons) should be removed and named entities (e.g., Rwanda) should be pseudo-anonymized before training to avoid models' bias and increase their generalization capabilities. We evaluate this methodology with internal dataset and external dataset before and after applying extended data preprocessing and named entity replacement. The results show that our proposal enhances on average the performance of a disinformation classification method with external test data in 65.78% without a significant decrease of the internal test performance.
Large language models (LLMs) have facilitated the generation of high-quality, cost-effective synthetic data for developing downstream models and conducting statistical analyses in various domains. However, the increased reliance on synthetic data may pose potential negative impacts. Numerous studies have demonstrated that LLM-generated synthetic data can perpetuate and even amplify societal biases and stereotypes, and produce erroneous outputs known as ``hallucinations'' that deviate from factual knowledge. In this paper, we aim to audit artifacts, such as classifiers, generators, or statistical plots, to identify those trained on or derived from synthetic data and raise user awareness, thereby reducing unexpected consequences and risks in downstream applications. To this end, we take the first step to introduce synthetic artifact auditing to assess whether a given artifact is derived from LLM-generated synthetic data. We then propose an auditing framework with three methods including metric-based auditing, tuning-based auditing, and classification-based auditing. These methods operate without requiring the artifact owner to disclose proprietary training details. We evaluate our auditing framework on three text classification tasks, two text summarization tasks, and two data visualization tasks across three training scenarios. Our evaluation demonstrates the effectiveness of all proposed auditing methods across all these tasks. For instance, black-box metric-based auditing can achieve an average accuracy of $0.868 \pm 0.071$ for auditing classifiers and $0.880 \pm 0.052$ for auditing generators using only 200 random queries across three scenarios. We hope our research will enhance model transparency and regulatory compliance, ensuring the ethical and responsible use of synthetic data.
Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing methods may reduce certain parts of the memory required for fine-tuning, they still require caching all intermediate activations computed in the forward pass to update weights during the backward pass. In this work, we develop TokenTune, a method to reduce memory usage, specifically the memory to store intermediate activations, in the fine-tuning of transformer-based models. During the backward pass, TokenTune approximates the gradient computation by backpropagating through just a subset of input tokens. Thus, with TokenTune, only a subset of intermediate activations are cached during the forward pass. Also, TokenTune can be easily combined with existing methods like LoRA, further reducing the memory cost. We evaluate our approach on pre-trained transformer models with up to billions of parameters, considering the performance on multiple downstream tasks such as text classification and question answering in a few-shot learning setup. Overall, TokenTune achieves performance on par with full fine-tuning or representative memory-efficient fine-tuning methods, while greatly reducing the memory footprint, especially when combined with other methods with complementary memory reduction mechanisms. We hope that our approach will facilitate the fine-tuning of large transformers, in specializing them for specific domains or co-training them with other neural components from a larger system. Our code is available at https://github.com/facebookresearch/tokentune.
\begin{abstract} This paper comprehensively analyzes privacy policies in AR/VR applications, leveraging BERT, a state-of-the-art text classification model, to evaluate the clarity and thoroughness of these policies. By comparing the privacy policies of AR/VR applications with those of free and premium websites, this study provides a broad perspective on the current state of privacy practices within the AR/VR industry. Our findings indicate that AR/VR applications generally offer a higher percentage of positive segments than free content but lower than premium websites. The analysis of highlighted segments and words revealed that AR/VR applications strategically emphasize critical privacy practices and key terms. This enhances privacy policies' clarity and effectiveness.
Accurate sentiment analysis of texts is crucial for a variety of applications, such as understanding customer feedback, monitoring market trends, and detecting public sentiment. However, manually annotating large sentiment corpora for supervised learning is labor-intensive and time-consuming. Therefore, it is essential and effective to develop a semi-supervised method for the sentiment analysis task. Although some methods have been proposed for semi-supervised text classification, they rely on the intrinsic information within the unlabeled data and the learning capability of the NLP model, which lack generalization ability to the sentiment analysis scenario and may prone to overfit. Inspired by the ability of pretrained Large Language Models (LLMs) in following instructions and generating coherent text, we propose a Semantic Consistency Regularization with Large Language Models (SCR) framework for semi-supervised sentiment analysis. We introduce two prompting strategies to semantically enhance unlabeled text using LLMs. The first is Entity-based Enhancement (SCR-EE), which involves extracting entities and numerical information, and querying the LLM to reconstruct the textual information. The second is Concept-based Enhancement (SCR-CE), which directly queries the LLM with the original sentence for semantic reconstruction. Subsequently, the LLM-augmented data is utilized for a consistency loss with confidence thresholding, which preserves high-quality agreement samples to provide additional supervision signals during training. Furthermore, to fully utilize the uncertain unlabeled data samples, we propose a class re-assembling strategy inspired by the class space shrinking theorem. Experiments show our method achieves remarkable performance over prior semi-supervised methods.
Spiking neural networks (SNNs) are bio-inspired networks that mimic how neurons in the brain communicate through discrete spikes, which have great potential in various tasks due to their energy efficiency and temporal processing capabilities. SNNs with self-attention mechanisms (spiking Transformers) have recently shown great advancements in various tasks, and inspired by traditional Transformers, several studies have demonstrated that spiking absolute positional encoding can help capture sequential relationships for input data, enhancing the capabilities of spiking Transformers for tasks such as sequential modeling and image classification. However, how to incorporate relative positional information into SNNs remains a challenge. In this paper, we introduce several strategies to approximate relative positional encoding (RPE) in spiking Transformers while preserving the binary nature of spikes. Firstly, we formally prove that encoding relative distances with Gray Code ensures that the binary representations of positional indices maintain a constant Hamming distance whenever their decimal values differ by a power of two, and we propose Gray-PE based on this property. In addition, we propose another RPE method called Log-PE, which combines the logarithmic form of the relative distance matrix directly into the spiking attention map. Furthermore, we extend our RPE methods to a two-dimensional form, making them suitable for processing image patches. We evaluate our RPE methods on various tasks, including time series forecasting, text classification, and patch-based image classification, and the experimental results demonstrate a satisfying performance gain by incorporating our RPE methods across many architectures.
This survey provides an overview of the challenges of misspellings in natural language processing (NLP). While often unintentional, misspellings have become ubiquitous in digital communication, especially with the proliferation of Web 2.0, user-generated content, and informal text mediums such as social media, blogs, and forums. Even if humans can generally interpret misspelled text, NLP models frequently struggle to handle it: this causes a decline in performance in common tasks like text classification and machine translation. In this paper, we reconstruct a history of misspellings as a scientific problem. We then discuss the latest advancements to address the challenge of misspellings in NLP. Main strategies to mitigate the effect of misspellings include data augmentation, double step, character-order agnostic, and tuple-based methods, among others. This survey also examines dedicated data challenges and competitions to spur progress in the field. Critical safety and ethical concerns are also examined, for example, the voluntary use of misspellings to inject malicious messages and hate speech on social networks. Furthermore, the survey explores psycholinguistic perspectives on how humans process misspellings, potentially informing innovative computational techniques for text normalization and representation. Finally, the misspelling-related challenges and opportunities associated with modern large language models are also analyzed, including benchmarks, datasets, and performances of the most prominent language models against misspellings. This survey aims to be an exhaustive resource for researchers seeking to mitigate the impact of misspellings in the rapidly evolving landscape of NLP.
Transformer-based models have achieved remarkable results in natural language processing (NLP) tasks such as text classification and machine translation. However, their computational complexity and resource demands pose challenges for scalability and accessibility. This research proposes a hybrid quantum-classical transformer model that integrates a quantum-enhanced attention mechanism to address these limitations. By leveraging quantum kernel similarity and variational quantum circuits (VQC), the model captures intricate token dependencies while improving computational efficiency. Experimental results on the IMDb dataset demonstrate that the quantum-enhanced model outperforms the classical baseline across all key metrics, achieving a 1.5% improvement in accuracy (65.5% vs. 64%), precision, recall, and F1 score. Statistical significance tests validate these improvements, highlighting the robustness of the quantum approach. These findings illustrate the transformative potential of quantum-enhanced attention mechanisms in optimizing NLP architectures for real-world applications.
Idiom detection using Natural Language Processing (NLP) is the computerized process of recognizing figurative expressions within a text that convey meanings beyond the literal interpretation of the words. While idiom detection has seen significant progress across various languages, the Kurdish language faces a considerable research gap in this area despite the importance of idioms in tasks like machine translation and sentiment analysis. This study addresses idiom detection in Sorani Kurdish by approaching it as a text classification task using deep learning techniques. To tackle this, we developed a dataset containing 10,580 sentences embedding 101 Sorani Kurdish idioms across diverse contexts. Using this dataset, we developed and evaluated three deep learning models: KuBERT-based transformer sequence classification, a Recurrent Convolutional Neural Network (RCNN), and a BiLSTM model with an attention mechanism. The evaluations revealed that the transformer model, the fine-tuned BERT, consistently outperformed the others, achieving nearly 99% accuracy while the RCNN achieved 96.5% and the BiLSTM 80%. These results highlight the effectiveness of Transformer-based architectures in low-resource languages like Kurdish. This research provides a dataset, three optimized models, and insights into idiom detection, laying a foundation for advancing Kurdish NLP.
The rapid advancement of large language models (LLMs) has made detecting AI-generated text an increasingly critical challenge. Traditional methods often fail to capture the nuanced semantic differences between human and machine-generated content. We therefore propose a novel approach based on semantic similarity analysis, leveraging a multi-layered architecture that combines a pre-trained DeBERTa-v3-large model, Bi-directional LSTMs, and linear attention pooling to capture both local and global semantic patterns. To enhance performance, we employ advanced input and output augmentation techniques such as sector-level context integration and wide output configurations. These techniques enable the model to learn more discriminative features and generalize across diverse domains. Experimental results show that this approach works better than traditional methods, proving its usefulness for AI-generated text detection and other text comparison tasks.
Recent approaches in hierarchical text classification (HTC) rely on the capabilities of a pre-trained transformer model and exploit the label semantics and a graph encoder for the label hierarchy. In this paper, we introduce an effective hierarchical text classifier RADAr (Transformer-based Autoregressive Decoder Architecture) that is based only on an off-the-shelf RoBERTa transformer to process the input and a custom autoregressive decoder with two decoder layers for generating the classification output. Thus, unlike existing approaches for HTC, the encoder of RADAr has no explicit encoding of the label hierarchy and the decoder solely relies on the label sequences of the samples observed during training. We demonstrate on three benchmark datasets that RADAr achieves results competitive to the state of the art with less training and inference time. Our model consistently performs better when organizing the label sequences from children to parents versus the inverse, as done in existing HTC approaches. Our experiments show that neither the label semantics nor an explicit graph encoder for the hierarchy is needed. This has strong practical implications for HTC as the architecture has fewer requirements and provides a speed-up by a factor of 2 at inference time. Moreover, training a separate decoder from scratch in conjunction with fine-tuning the encoder allows future researchers and practitioners to exchange the encoder part as new models arise. The source code is available at https://github.com/yousef-younes/RADAr.
Attention maps in neural models for NLP are appealing to explain the decision made by a model, hopefully emphasizing words that justify the decision. While many empirical studies hint that attention maps can provide such justification from the analysis of sound examples, only a few assess the plausibility of explanations based on attention maps, i.e., the usefulness of attention maps for humans to understand the decision. These studies furthermore focus on text classification. In this paper, we report on a preliminary assessment of attention maps in a sentence comparison task, namely natural language inference. We compare the cross-attention weights between two RNN encoders with human-based and heuristic-based annotations on the eSNLI corpus. We show that the heuristic reasonably correlates with human annotations and can thus facilitate evaluation of plausible explanations in sentence comparison tasks. Raw attention weights however remain only loosely related to a plausible explanation.
This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in capturing deep semantic relationships and optimizing computational complexity, this paper introduces a multi-level attention mechanism and a contrastive learning strategy. The multi-level attention mechanism effectively models the global semantics and local features in the text by combining global attention with local attention; the contrastive learning strategy enhances the model's ability to distinguish between different categories by constructing positive and negative sample pairs while improving the classification effect. In addition, in order to improve the training and inference efficiency of the model on large-scale text data, this paper designs a lightweight module to optimize the feature transformation process and reduce the computational cost. Experimental results on the dataset show that the improved Transformer model outperforms the comparative models such as BiLSTM, CNN, standard Transformer, and BERT in terms of classification accuracy, F1 score, and recall rate, showing stronger semantic representation ability and generalization performance. The method proposed in this paper provides a new idea for algorithm optimization in the field of text classification and has good application potential and practical value. Future work will focus on studying the performance of this model in multi-category imbalanced datasets and cross-domain tasks and explore the integration wi
Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision. Empirical studies postulate that attention maps can be provided as an explanation for model output. However, it is still questionable to ask whether this explanation helps regular people to understand and accept the model output (the plausibility of the explanation). Recent studies show that attention weights in the RNN encoders are hardly plausible because they spread on input tokens. We thus propose 3 additional constraints to the learning objective function to improve the plausibility of the attention map: regularization to increase the attention weight sparsity, semi-supervision to supervise the map by a heuristic and supervision by human annotation. Results show that all techniques can improve the attention map plausibility at some level. We also observe that specific instructions for human annotation might have a negative effect on classification performance. Beyond the attention map, the result of experiments on text classification tasks also shows that no matter how the constraint brings the gain, the contextualization layer plays a crucial role in finding the right space for finding plausible tokens.
This research introduces a hybrid classical-quantum framework for text classification, integrating GPT-Neo 125M with Low-Rank Adaptation (LoRA) and Synthetic Minority Over-sampling Technique (SMOTE) using quantum computing backends. While the GPT-Neo 125M baseline remains the best-performing model, the implementation of LoRA and SMOTE enhances the hybrid model, resulting in improved accuracy, faster convergence, and better generalization. Experiments on IBM's 127-qubit quantum backend and Pennylane's 32-qubit simulation demonstrate the viability of combining classical neural networks with quantum circuits. This framework underscores the potential of hybrid architectures for advancing natural language processing applications.
Text embeddings are numerical representations of text data, where words, phrases, or entire documents are converted into vectors of real numbers. These embeddings capture semantic meanings and relationships between text elements in a continuous vector space. The primary goal of text embeddings is to enable the processing of text data by machine learning models, which require numerical input. Numerous embedding models have been developed for various applications. This paper presents our work in evaluating different embeddings through a comprehensive comparative analysis of four distinct models, focusing on their text classification efficacy. We employ both K-Nearest Neighbors (KNN) and Logistic Regression (LR) to perform binary classification tasks, specifically determining whether a text snippet is associated with 'delay' or 'not delay' within a labeled dataset. Our research explores the use of text snippet embeddings for training supervised text classification models to identify delay-related statements during the document review process of construction delay disputes. The results of this study highlight the potential of embedding models to enhance the efficiency and accuracy of document analysis in legal contexts, paving the way for more informed decision-making in complex investigative scenarios.