Both encoder-only models (e.g., BERT, RoBERTa) and large language models (LLMs, e.g., Llama3) have been widely used for text classification tasks. However, there is a lack of systematic studies comparing the performance of encoder-based models and LLMs in text classification, particularly when fine-tuning is involved. This study employed a diverse range of models and methods, varying in size and architecture, and including both fine-tuned and pre-trained approaches. We first assessed the performances of these LLMs on the 20 Newsgroups (20NG) and MASSIVE datasets, comparing them to encoder-only RoBERTa models. Additionally, we explored the multi-task capabilities of both model types by combining multiple classification tasks, including intent detection and slot-filling, into a single model using data from both datasets. Our results indicate that fully fine-tuned Llama3-70B models outperform RoBERTa-large and other decoder LLMs across various classification tasks and datasets. Moreover, the consolidated multi-task fine-tuned LLMs matched the performance of dual-model setups in both tasks across both datasets. Overall, our study provides a comprehensive benchmark of encoder-only and LLM models on text classification tasks and demonstrates a method to combine two or more fully fine-tuned decoder LLMs for reduced latency and equivalent performance.
In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can enhance their performance in text classification through fine-tuning. However, existing data quality research based on LLMs is challenging to apply directly to solve text classification problems. To further improve the performance of LLMs in classification tasks, this paper proposes a data quality enhancement (DQE) method for text classification based on LLMs. This method starts by using a greedy algorithm to select data, dividing the dataset into sampled and unsampled subsets, and then performing fine-tuning of the LLMs using the sampled data. Subsequently, this model is used to predict the outcomes for the unsampled data, categorizing incorrectly predicted data into uncovered, difficult, and noisy data. Experimental results demonstrate that our method effectively enhances the performance of LLMs in text classification tasks and significantly improves training efficiency, saving nearly half of the training time. Our method has achieved state-of-the-art performance in several open-source classification tasks.
This study aims to explore the performance improvement method of large language models based on GPT-4 under the multi-task learning framework and conducts experiments on two tasks: text classification and automatic summary generation. Through the combined design of shared feature extractors and task-specific modules, we achieve knowledge-sharing and optimization of multiple tasks in the same model. The experiment uses multiple subtasks of the GLUE dataset to compare the performance of the multi-task model with the single-task GPT-4, the multi-task version of GPT-3, the BERT basic model, and the classic Bi-LSTM with Attention model. The results show that the proposed multi-task learning model outperforms other comparison models in terms of text classification accuracy and ROUGE value of summary generation, demonstrating the advantages of multi-task learning in improving model generalization ability and collaborative learning between tasks. The model maintains a stable loss convergence rate during training, showing good learning efficiency and adaptability to the test set. This study verifies the applicability of the multi-task learning framework in large language models, especially in improving the model's ability to balance different tasks. In the future, with the combination of large language models and multimodal data and the application of dynamic task adjustment technology, the framework based on multi-task learning is expected to play a greater role in practical applications across fields and provide new ideas for the development of general artificial intelligence.
Diversity in demonstration selection is crucial for enhancing model generalization, as it enables a broader coverage of structures and concepts. However, constructing an appropriate set of demonstrations has remained a focal point of research. This paper presents the Relevance-Diversity Enhanced Selection (RDES), an innovative approach that leverages reinforcement learning to optimize the selection of diverse reference demonstrations for text classification tasks using Large Language Models (LLMs), especially in few-shot prompting scenarios. RDES employs a Q-learning framework to dynamically identify demonstrations that maximize both diversity and relevance to the classification objective by calculating a diversity score based on label distribution among selected demonstrations. This method ensures a balanced representation of reference data, leading to improved classification accuracy. Through extensive experiments on four benchmark datasets and involving 12 closed-source and open-source LLMs, we demonstrate that RDES significantly enhances classification accuracy compared to ten established baselines. Furthermore, we investigate the incorporation of Chain-of-Thought (CoT) reasoning in the reasoning process, which further enhances the model's predictive performance. The results underscore the potential of reinforcement learning to facilitate adaptive demonstration selection and deepen the understanding of classification challenges.
Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My dissertation focuses on developing intrinsically interpretable models when using LMs as encoders while maintaining their superior performance via prototypical networks. I initiated my research by investigating enhancements in performance for interpretable models of sarcasm detection. My proposed approach focuses on capturing sentiment incongruity to enhance accuracy while offering instance-based explanations for the classification decisions. Later, I developed a novel white-box multi-head graph attention-based prototype network designed to explain the decisions of text classification models without sacrificing the accuracy of the original black-box LMs. In addition, I am working on extending the attention-based prototype network with contrastive learning to redesign an interpretable graph neural network, aiming to enhance both the interpretability and performance of the model in document classification.
The effectiveness of Large Language Models (LLMs) significantly relies on the quality of the prompts they receive. However, even when processing identical prompts, LLMs can yield varying outcomes due to differences in their training processes. To leverage the collective intelligence of multiple LLMs and enhance their performance, this study investigates three majority voting strategies for text classification, focusing on phishing URL detection. The strategies are: (1) a prompt-based ensemble, which utilizes majority voting across the responses generated by a single LLM to various prompts; (2) a model-based ensemble, which entails aggregating responses from multiple LLMs to a single prompt; and (3) a hybrid ensemble, which combines the two methods by sending different prompts to multiple LLMs and then aggregating their responses. Our analysis shows that ensemble strategies are most suited in cases where individual components exhibit equivalent performance levels. However, when there is a significant discrepancy in individual performance, the effectiveness of the ensemble method may not exceed that of the highest-performing single LLM or prompt. In such instances, opting for ensemble techniques is not recommended.
The exponential growth of online textual content across diverse domains has necessitated advanced methods for automated text classification. Large Language Models (LLMs) based on transformer architectures have shown significant success in this area, particularly in natural language processing (NLP) tasks. However, general-purpose LLMs often struggle with domain-specific content, such as scientific texts, due to unique challenges like specialized vocabulary and imbalanced data. In this study, we fine-tune four state-of-the-art LLMs BERT, SciBERT, BioBERT, and BlueBERT on three datasets derived from the WoS-46985 dataset to evaluate their performance in scientific text classification. Our experiments reveal that domain-specific models, particularly SciBERT, consistently outperform general-purpose models in both abstract-based and keyword-based classification tasks. Additionally, we compare our achieved results with those reported in the literature for deep learning models, further highlighting the advantages of LLMs, especially when utilized in specific domains. The findings emphasize the importance of domain-specific adaptations for LLMs to enhance their effectiveness in specialized text classification tasks.
In social media, neural network models have been applied to hate speech detection, sentiment analysis, etc., but neural network models are susceptible to adversarial attacks. For instance, in a text classification task, the attacker elaborately introduces perturbations to the original texts that hardly alter the original semantics in order to trick the model into making different predictions. By studying textual adversarial attack methods, the robustness of language models can be evaluated and then improved. Currently, most of the research in this field focuses on English, and there is also a certain amount of research on Chinese. However, there is little research targeting Chinese minority languages. With the rapid development of artificial intelligence technology and the emergence of Chinese minority language models, textual adversarial attacks become a new challenge for the information processing of Chinese minority languages. In response to this situation, we propose a multi-granularity Tibetan textual adversarial attack method based on masked language models called TSTricker. We utilize the masked language models to generate candidate substitution syllables or words, adopt the scoring mechanism to determine the substitution order, and then conduct the attack method on several fine-tuned victim models. The experimental results show that TSTricker reduces the accuracy of the classification models by more than 28.70% and makes the classification models change the predictions of more than 90.60% of the samples, which has an evidently higher attack effect than the baseline method.
The semi-supervised learning (SSL) strategy in lightweight models requires reducing annotated samples and facilitating cost-effective inference. However, the constraint on model parameters, imposed by the scarcity of training labels, limits the SSL performance. In this paper, we introduce PS-NET, a novel framework tailored for semi-supervised text mining with lightweight models. PS-NET incorporates online distillation to train lightweight student models by imitating the Teacher model. It also integrates an ensemble of student peers that collaboratively instruct each other. Additionally, PS-NET implements a constant adversarial perturbation schema to further self-augmentation by progressive generalizing. Our PS-NET, equipped with a 2-layer distilled BERT, exhibits notable performance enhancements over SOTA lightweight SSL frameworks of FLiText and DisCo in SSL text classification with extremely rare labelled data.
The TextClass Benchmark project is an ongoing, continuous benchmarking process that aims to provide a comprehensive, fair, and dynamic evaluation of LLMs and transformers for text classification tasks. This evaluation spans various domains and languages in social sciences disciplines engaged in NLP and text-as-data approach. The leaderboards present performance metrics and relative ranking using a tailored Elo rating system. With each leaderboard cycle, novel models are added, fixed test sets can be replaced for unseen, equivalent data to test generalisation power, ratings are updated, and a Meta-Elo leaderboard combines and weights domain-specific leaderboards. This article presents the rationale and motivation behind the project, explains the Elo rating system in detail, and estimates Meta-Elo across different classification tasks in social science disciplines. We also present a snapshot of the first cycle of classification tasks on incivility data in Chinese, English, German and Russian. This ongoing benchmarking process includes not only additional languages such as Arabic, Hindi, and Spanish but also a classification of policy agenda topics, misinformation, among others.
Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks. However, the underlying mechanism of this enhancement remains obscure. Previous studies rely on individual words for interpreting continuous prompts, which lacks comprehensive semantic understanding. Drawing inspiration from Concept Bottleneck Models, we propose a framework for interpreting continuous prompts by decomposing them into human-readable concepts. Specifically, to ensure the feasibility of the decomposition, we demonstrate that a corresponding concept embedding matrix and a coefficient matrix can always be found to replace the prompt embedding matrix. Then, we employ GPT-4o to generate a concept pool and choose potential candidate concepts that are discriminative and representative using a novel submodular optimization algorithm. Experiments demonstrate that our framework can achieve similar results as the original P-tuning and word-based approaches using only a few concepts while providing more plausible results. Our code is available at https://github.com/qq31415926/CD.
Large Language Models (LLMs) have shown impressive performance on various benchmarks, yet their ability to engage in deliberate reasoning remains questionable. We present NYT-Connections, a collection of 358 simple word classification puzzles derived from the New York Times Connections game. This benchmark is designed to penalize quick, intuitive "System 1" thinking, isolating fundamental reasoning skills. We evaluated six recent LLMs, a simple machine learning heuristic, and humans across three configurations: single-attempt, multiple attempts without hints, and multiple attempts with contextual hints. Our findings reveal a significant performance gap: even top-performing LLMs like GPT-4 fall short of human performance by nearly 30%. Notably, advanced prompting techniques such as Chain-of-Thought and Self-Consistency show diminishing returns as task difficulty increases. NYT-Connections uniquely combines linguistic isolation, resistance to intuitive shortcuts, and regular updates to mitigate data leakage, offering a novel tool for assessing LLM reasoning capabilities.
Deep learning has achieved remarkable success in processing and managing unstructured data. However, its "black box" nature imposes significant limitations, particularly in sensitive application domains. While existing interpretable machine learning methods address some of these issues, they often fail to adequately consider feature correlations and provide insufficient evaluation of model decision paths. To overcome these challenges, this paper introduces Real Explainer (RealExp), an interpretability computation method that decouples the Shapley Value into individual feature importance and feature correlation importance. By incorporating feature similarity computations, RealExp enhances interpretability by precisely quantifying both individual feature contributions and their interactions, leading to more reliable and nuanced explanations. Additionally, this paper proposes a novel interpretability evaluation criterion focused on elucidating the decision paths of deep learning models, going beyond traditional accuracy-based metrics. Experimental validations on two unstructured data tasks -- image classification and text sentiment analysis -- demonstrate that RealExp significantly outperforms existing methods in interpretability. Case studies further illustrate its practical value: in image classification, RealExp aids in selecting suitable pre-trained models for specific tasks from an interpretability perspective; in text classification, it enables the optimization of models and approximates the performance of a fine-tuned GPT-Ada model using traditional bag-of-words approaches.
With the ever-increasing number of news stories available online, classifying them by topic, regardless of the language they are written in, has become crucial for enhancing readers' access to relevant content. To address this challenge, we propose a teacher-student framework based on large language models (LLMs) for developing multilingual news classification models of reasonable size with no need for manual data annotation. The framework employs a Generative Pretrained Transformer (GPT) model as the teacher model to develop an IPTC Media Topic training dataset through automatic annotation of news articles in Slovenian, Croatian, Greek, and Catalan. The teacher model exhibits a high zero-shot performance on all four languages. Its agreement with human annotators is comparable to that between the human annotators themselves. To mitigate the computational limitations associated with the requirement of processing millions of texts daily, smaller BERT-like student models are fine-tuned on the GPT-annotated dataset. These student models achieve high performance comparable to the teacher model. Furthermore, we explore the impact of the training data size on the performance of the student models and investigate their monolingual, multilingual and zero-shot cross-lingual capabilities. The findings indicate that student models can achieve high performance with a relatively small number of training instances, and demonstrate strong zero-shot cross-lingual abilities. Finally, we publish the best-performing news topic classifier, enabling multilingual classification with the top-level categories of the IPTC Media Topic schema.
Hierarchical Text Classification (HTC) is a natural language processing task with the objective to classify text documents into a set of classes from a structured class hierarchy. Many HTC approaches have been proposed which attempt to leverage the class hierarchy information in various ways to improve classification performance. Machine learning-based classification approaches require large amounts of training data and are most-commonly compared through three established benchmark datasets, which include the Web Of Science (WOS), Reuters Corpus Volume 1 Version 2 (RCV1-V2) and New York Times (NYT) datasets. However, apart from the RCV1-V2 dataset which is well-documented, these datasets are not accompanied with detailed description methodologies. In this paper, we introduce three new HTC benchmark datasets in the domain of research publications which comprise the titles and abstracts of papers from the Web of Science publication database. We first create two baseline datasets which use existing journal-and citation-based classification schemas. Due to the respective shortcomings of these two existing schemas, we propose an approach which combines their classifications to improve the reliability and robustness of the dataset. We evaluate the three created datasets with a clustering-based analysis and show that our proposed approach results in a higher quality dataset where documents that belong to the same class are semantically more similar compared to the other datasets. Finally, we provide the classification performance of four state-of-the-art HTC approaches on these three new datasets to provide baselines for future studies on machine learning-based techniques for scientific publication classification.
Graph contrastive learning has been successfully applied in text classification due to its remarkable ability for self-supervised node representation learning. However, explicit graph augmentations may lead to a loss of semantics in the contrastive views. Secondly, existing methods tend to overlook edge features and the varying significance of node features during multi-graph learning. Moreover, the contrastive loss suffer from false negatives. To address these limitations, we propose a novel method of contrastive multi-graph learning with neighbor hierarchical sifting for semi-supervised text classification, namely ConNHS. Specifically, we exploit core features to form a multi-relational text graph, enhancing semantic connections among texts. By separating text graphs, we provide diverse views for contrastive learning. Our approach ensures optimal preservation of the graph information, minimizing data loss and distortion. Then, we separately execute relation-aware propagation and cross-graph attention propagation, which effectively leverages the varying correlations between nodes and edge features while harmonising the information fusion across graphs. Subsequently, we present the neighbor hierarchical sifting loss (NHS) to refine the negative selection. For one thing, following the homophily assumption, NHS masks first-order neighbors of the anchor and positives from being negatives. For another, NHS excludes the high-order neighbors analogous to the anchor based on their similarities. Consequently, it effectively reduces the occurrence of false negatives, preventing the expansion of the distance between similar samples in the embedding space. Our experiments on ThuCNews, SogouNews, 20 Newsgroups, and Ohsumed datasets achieved 95.86\%, 97.52\%, 87.43\%, and 70.65\%, which demonstrates competitive results in semi-supervised text classification.
The integration of new literature into the English curriculum remains a challenge since educators often lack scalable tools to rapidly evaluate readability and adapt texts for diverse classroom needs. This study proposes to address this gap through a multimodal approach that combines transformer-based text classification with linguistic feature analysis to align texts with UK Key Stages. Eight state-of-the-art Transformers were fine-tuned on segmented text data, with BERT achieving the highest unimodal F1 score of 0.75. In parallel, 500 deep neural network topologies were searched for the classification of linguistic characteristics, achieving an F1 score of 0.392. The fusion of these modalities shows a significant improvement, with every multimodal approach outperforming all unimodal models. In particular, the ELECTRA Transformer fused with the neural network achieved an F1 score of 0.996. Unimodal and multimodal approaches are shown to have statistically significant differences in all validation metrics (accuracy, precision, recall, F1 score) except for inference time. The proposed approach is finally encapsulated in a stakeholder-facing web application, providing non-technical stakeholder access to real-time insights on text complexity, reading difficulty, curriculum alignment, and recommendations for learning age range. The application empowers data-driven decision making and reduces manual workload by integrating AI-based recommendations into lesson planning for English literature.
Natural Language Processing (NLP) is revolutionising the way legal professionals and laypersons operate in the legal field. The considerable potential for NLP in the legal sector, especially in developing computational tools for various legal processes, has captured the interest of researchers for years. This survey follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework, reviewing 154 studies, with a final selection of 133 after manual filtering. It explores foundational concepts related to NLP in the legal domain, illustrating the unique aspects and challenges of processing legal texts, such as extensive document length, complex language, and limited open legal datasets. We provide an overview of NLP tasks specific to legal text, such as Legal Document Summarisation, legal Named Entity Recognition, Legal Question Answering, Legal Argument Mining, Legal Text Classification, and Legal Judgement Prediction. In the section on legal Language Models (LMs), we analyse both developed LMs and approaches for adapting general LMs to the legal domain. Additionally, we identify 16 Open Research Challenges, including bias in Artificial Intelligence applications, the need for more robust and interpretable models, and improving explainability to handle the complexities of legal language and reasoning.
Peer review in grant evaluation informs funding decisions, but the contents of peer review reports are rarely analyzed. In this work, we develop a thoroughly tested pipeline to analyze the texts of grant peer review reports using methods from applied Natural Language Processing (NLP) and machine learning. We start by developing twelve categories reflecting content of grant peer review reports that are of interest to research funders. This is followed by multiple human annotators' iterative annotation of these categories in a novel text corpus of grant peer review reports submitted to the Swiss National Science Foundation. After validating the human annotation, we use the annotated texts to fine-tune pre-trained transformer models to classify these categories at scale, while conducting several robustness and validation checks. Our results show that many categories can be reliably identified by human annotators and machine learning approaches. However, the choice of text classification approach considerably influences the classification performance. We also find a high correspondence between out-of-sample classification performance and human annotators' perceived difficulty in identifying categories. Our results and publicly available fine-tuned transformer models will allow researchers and research funders and anybody interested in peer review to examine and report on the contents of these reports in a structured manner. Ultimately, we hope our approach can contribute to ensuring the quality and trustworthiness of grant peer review.
The exponential growth of textual data presents substantial challenges in management and analysis, notably due to high storage and processing costs. Text classification, a vital aspect of text mining, provides robust solutions by enabling efficient categorization and organization of text data. These techniques allow individuals, researchers, and businesses to derive meaningful patterns and insights from large volumes of text. This survey paper introduces a comprehensive taxonomy specifically designed for text classification based on research fields. The taxonomy is structured into hierarchical levels: research field-based category, research field-based sub-category, methodology-based technique, methodology sub-technique, and research field applications. We employ a dual evaluation approach: empirical and experimental. Empirically, we assess text classification techniques across four critical criteria. Experimentally, we compare and rank the methodology sub-techniques within the same methodology technique and within the same overall research field sub-category. This structured taxonomy, coupled with thorough evaluations, provides a detailed and nuanced understanding of text classification algorithms and their applications, empowering researchers to make informed decisions based on precise, field-specific insights.