A Study on Text Classification in the Age of Large Language Models

BackgroundDisease name recognition is a fundamental task in clinical natural language processing, enabling the extraction of critical patient information from electronic health records. While recent advances in large language models (LLMs) have shown promise, most evaluations have focused on English, and little is known about their robustness in low-resource languages such as Japanese. In particular, whether these models can perform reliably on previously unseen in-hospital data, which differs from training data in writing styles and clinical contexts, has not been thoroughly investigated.ObjectiveThis study evaluated the robustness of fine-tuned LLMs for disease name recognition in Japanese clinical notes, with a particular focus on their performance on in-hospital data that was not included during training.MethodsWe used two corpora for this study: (1) a publicly available set of Japanese case reports denoted as CR, and (2) a newly constructed corpus of progress notes, denoted as PN, written by ten physicians to capture stylistic variations of in-hospital clinical notes. To reflect real-world deployment scenarios, we first fine-tuned models on CR. Specifically, we compared a LLM and a baseline-masked language model (MLM). These models were then evaluated under two conditions: (1) on CR, representing the in-domain (ID) setting with the same document type, similar to training, and (2) on PN, representing the out-of-domain (OOD) setting with a different document type. Robustness was assessed by calculating the performance gap (ie, the performance drop from in-domain to out-of-domain settings).ResultsThe LLM demonstrated greater robustness, with a smaller performance gap in F1-scores (ID–OOD = −8.6) compared to the MLM baseline performance (ID–OOD = −13.9). This indicated more stable performance across ID and OOD settings, highlighting the effectiveness of fine-tuned LLMs for reliable use in diverse clinical settings.ConclusionsFine-tuned LLMs demonstrate superior robustness for disease name recognition in Japanese clinical notes, with a smaller performance gap. These findings highlight the potential of LLMs as reliable tools for clinical natural language processing in low-resource language settings and support their deployment in real-world health care applications, where diversity in documentation is inevitable.

While large language models (LLMs) have shown promise in medical text analysis, their application in automated medical billing code extraction remains underexplored, particularly for the German medical fee schedule system (GOÄ). Therefore, an LLM was fine-tuned to perform multi-label classification of GOÄ codes from radiology reports automatically, and its performance was compared with state-of-the-art commercial and open-source LLMs. Following ethics committee approval, we analyzed 499,601 radiology reports from 124,497 patients, containing 1,799,971 manually identified GOÄ codes as ground truth. The MediPhi-Instruct 4B model was fine-tuned using five-fold cross-validation. Performance was evaluated on the hold-out test set and compared against GPT-5, GPT-4.1, GPT-oss, Kimi-K2, Deepseek-R1, Deepseek-V3, Gemini 2.5, Llama-70B, and Qwen-3 LLMs on a subset of 500 anonymized and 350 cleaned reports using zero-shot and few-shot prompting techniques. The fine-tuned model achieved an accuracy of 77.15% ± 0.47% and a micro-average F1-score of 87.79% ± 0.31% on the hold-out test set. On a subset of 500 real-world samples, our models outperformed the best-performing LLM, Gemini 2.5 Flash, with an F1-score of 70.32% ± 1.54% compared to 58.22% ± 1.50% (p < 0.001). For the cleaned dataset of 350 samples, GPT-5 achieved the best F1-score of 89.51 ± 1.52% and outperformed the fine-tuned models (p < 0.001). Fine-tuned LLMs can effectively automate GOÄ code classification from radiology reports, with the potential of outperforming commercial LLMs. This approach shows promise for improving billing efficiency and accuracy in healthcare settings, though manual verification is still recommended. Question LLMs with high parameters possess medical knowledge, but how effective are they at predicting billing codes from radiology reports compared to smaller, fine-tuned models? Finidngs A fine-tuned ensemble model achieved competitive results and can outperform larger, proprietary LLMs. Clinical relevance Smaller, fine-tuned models offer an efficient alternative to proprietary LLMs in generating billing codes and can be integrated to assist clinical coding. This technology has the potential to transform clinical billing procedures, but its use should be overseen by qualified professional personnel.

In recent years, with the rapid development of large language models, optimizing BERT's performance on small-scale datasets using large language models has gradually become a research hotspot. To this end, this paper proposes a data augmentation method based on large language models to enhance BERT's performance in text classification tasks. Specifically, we first use large language models to back-translate the training data. By translating the text into other languages and then back into the original language, we generate new samples that are semantically consistent but have diverse expressions, thereby increasing the diversity of the training data. Subsequently, the augmented training set is used to train the BERT model, which significantly improves classification accuracy on the Reuters News Classification dataset. Experimental results show that this method effectively mitigates the limitations of small-scale datasets and significantly enhances the model's generalization ability, providing a novel and efficient solution for text classification tasks.

Evaluating gpt-4 for zero-shot classification of bleeding and clotting events: Can large language models serve as second reviewers?

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature, but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic approach that includes a low-cost knowledge acquisition process for acquiring domain knowledge, an effective knowledge infusion module for improving model performance, and a knowledge distillation component for reducing the model size and deploying K-PLMs on resource-restricted devices (e.g., CPU) for real-world application. Importantly, instead of capturing entity knowledge like the majority of existing K-PLMs, our approach captures relational knowledge, which contributes to better improving sentence-level text classification and text matching tasks that play a key role in question answering (QA). We conducted a set of experiments on five text classification tasks and three text matching tasks from three domains, namely E-commerce, Government, and Film&TV, and performed online A/B tests in E-commerce. Experimental results show that our approach is able to achieve substantial improvement on sentence-level question answering tasks and bring beneficial business value in industrial settings.

Large Language Models (LLMs) can analyze large datasets semantically. However, research on applying LLMs for mental health text classification is relatively new and developing. Existing methods often use supervised, deep, and reinforcement learning, which rely heavily on fine-tuning and reward models. To investigate whether LLMs can assist in recommending mental health apps based on user reviews, our study collected approximately 200k user reviews from 73 mental health mobile applications. We instructed selected LLMs to classify individual reviews into 1-5 star ratings, subsequently averaging these results to derive an overall rating for each app reflecting current user feedback. While the best supervised learning method in our experiments achieved an F1-Score of 0.79 which required significantly more human effort, the GPT-4 and Gemini 1.5 Pro delivered a strong ‘out-of-the-box’ performance with an overall F1-Score of 0.76. We provide further statistical comparisons and discussions of the performance of these models for the text classification task. Using a crowdsourcing platform to determine agreement levels, we observed that human ratings align closely with GPT ratings. In addition, we analyze specific features and concerns highlighted in mental health app reviews. Alongside our analysis, we make our data available for further experimentation and benchmarking.

In this study, we perform a comprehensive evaluation of sentiment classification for German language data using three different approaches: (1) dictionary-based methods, (2) fine-tuned transformer models such as BERT and XLM-T and (3) various large language models (LLMs) with zero-shot capabilities, including natural language inference models, Siamese models and dialog-based models. The evaluation considers a variety of German language datasets, including contemporary social media texts, product reviews and humanities datasets. Our results confirm that dictionary-based methods, while computationally efficient and interpretable, fall short in classification accuracy. Fine-tuned models offer strong performance, but require significant training data and computational resources. LLMs with zero-shot capabilities, particularly dialog-based models, demonstrate competitive performance, often rivaling fine-tuned models, while eliminating the need for task-specific training. However, challenges remain regarding non-determinism, prompt sensitivity and the high resource requirements of large LLMs. The results suggest that for sentiment analysis in the computational humanities, where non-English and historical language data are common, LLM-based zero-shot classification is a viable alternative to fine-tuned models and dictionaries. Nevertheless, model selection remains highly context-dependent, requiring careful consideration of trade-offs between accuracy, resource efficiency and transparency.

Prompt-engineered Large Language Models (LLMs) have gained widespread adoption across various applications due to their ability to perform complex tasks without requiring additional training. Despite their impressive performance, there is considerable scope for improvement, particularly in addressing the limitations of individual models. One promising avenue is the use of ensemble learning strategies, which combine the strengths of multiple models to enhance overall performance. In this study, we investigate the effectiveness of stacking ensemble techniques for chat-based LLMs in text classification tasks, with a focus on phishing URL detection. Notably, we introduce and evaluate three stacking methods: (1) prompt-based stacking , which uses multiple prompts to generate diverse responses from a single LLM; (2) model-based stacking , which combines responses from multiple LLMs using a unified prompt; (3) hybrid stacking , which integrates the first two approaches by employing multiple prompts across different LLMs to generate responses. For each of these methods, we explore meta-learners of varying complexities, ranging from Logistic Regression to BERT. Additionally, we investigate the impact of including the input text as a feature for the meta-learner. Our results demonstrate that stacking ensembles consistently outperform individual models, achieving superior performance with minimal training and computational overhead. These findings highlight the potential of stacking ensembles in mitigating the limitations of existing methods and significantly enhancing the efficiency and accuracy of chat-based LLMs for text classification tasks.

<sec> <title>BACKGROUND</title> Substance use disorder (SUD) affects more than 48 million people in the US, but access to care is often constrained by factors such as stigma, financial barriers, and limited service availability. While digital health interventions have begun to mitigate these challenges, large language models (LLMs) such as GPT introduce new possibilities for scalable SUD recovery support. However, empirical evidence regarding LLM use in SUD contexts re-mains fragmented and unevenly evaluated. A scoping review is needed to synthesize cur-rent approaches, surface methodological and safety gaps, and inform future research. </sec> <sec> <title>OBJECTIVE</title> This scoping review synthesizes current evidence on the use of LLMs in SUD and addiction contexts. It examines how LLM-based tools are being applied across the full spectrum of care, identifies common tasks and data sources, evaluates risks and safety concerns, and maps early evidence of effectiveness and gaps that inform future research. </sec> <sec> <title>METHODS</title> We conducted a scoping review in accordance with PRISMA-ScR guidelines. We searched medical and technical databases for studies that reported empirical findings on LLMs in drug-related SUD contexts. Of 675 records identified, 492 were screened at the title and abstract level, 60 underwent full-text review, and 12 studies met inclusion criteria. </sec> <sec> <title>RESULTS</title> All included studies were published in 2024 or 2025, indicating a very recent and rapidly evolving evidence base. Most studies used public social media or online forums (8 of 12), while 3 studies used clinical data such as EHR, and 1 study used multimodal data that combined sensors, images, and chat logs. GPT-family models were the most frequently used (10 of 12), often evaluated alongside Llama or Mistral models. Across studies, LLM applications clustered into four task categories: text classification and extraction, response generation, conversational decision support, and predictive modeling using LLM-derived features. Classification and extraction tasks were most common and often showed im-proved performance compared with traditional machine learning or rule-based baselines. While general-purpose LLMs were prone to generating stigmatizing, biased, or clinically inappropriate content in SUD-related scenarios, it was also reported that targeted prompt engineering substantially reduced stigmatizing language and improved perceived ade-quacy and appropriateness of responses. However, safety evaluations remained limited in scope and depth. </sec> <sec> <title>CONCLUSIONS</title> LLM-based tools show emerging potential to support SUD-related research and care, particularly scalable classification and information extraction, conversational screening, and feature derivation from unstructured text or speech. Yet current work is predominantly preclinical, relying on public datasets and simulated prompts, with limited evidence on safety, clinical effectiveness, or real-world implementation in recovery settings. Responsible use in SUD contexts will require a safety-first development approach that integrates human-in-the-loop validation, systematic prompt engineering, and design constraints such as curated response libraries. It will also require efforts to strengthen LLM literacy among clinicians, peer specialists, and people in recovery. </sec>

Extracting information from unstructured and semi-structured geoscience literature is a crucial step in conducting geological research. The traditional machine learning extraction paradigm requires a substantial amount of high-quality manually annotated data for model training, which is time-consuming, labor-intensive, and not easily transferable to new fields. Recently, large language models (LLMs) (e.g., ChatGPT, GPT-4, and LLaMA), have shown great performance in various natural language processing (NLP) tasks, such as question answering, machine translation, and text generation. A substantial body of work has demonstrated that LLMs possess strong in-context learning (ICL) and even zero-shot learning capabilities to solve downstream tasks without specifically designed supervised fine-tuning. In this paper, we propose utilizing LLMs for geoscience literature information extraction. Specifically, we design a hierarchical PDF parsing pipeline and an automated knowledge extraction process, which can significantly reduce the need for manual data annotation, assisting geoscientists in literature data mining. For the hierarchical PDF parsing pipeline, firstly, a document layout detection model fine-tuned on geoscience literature is employed for layout detection, obtaining layout detection information for the document. Secondly, based on the document layout information, an optical character content parsing model is used for content parsing, obtaining the text structure and plain text corresponding to the content. Finally, the text structure and plain text are combined and reconstructed to ultimately obtain the parsed structured data. For the automated knowledge extraction process, firstly, the parsed long text is segmented into paragraphs to adapt to the input length limit of LLMs. Subsequently, a few-shot prompting method is employed for structured knowledge extraction, encompassing two tasks: attribute value extraction and triplet extraction. In attribute value extraction, prompts are generated automatically by the LLMs based on the subdomain and attribute names, facilitating the location and extraction of values related to subdomain attribute names in the text. For triplet extraction, the LLMs employ a procedural approach to entity extraction, entity type extraction, and relation extraction, following the knowledge graph structure pattern. Finally, the extracted structured knowledge is stored in the form of knowledge graphs, facilitating further analysis and integration of various types of knowledge from the literature. Our proposed approach turns out to be simple, flexible, and highly effective in geoscience literature information extraction. Demonstrations of information extraction in subdomains such as radiolarian fossils and fluvial facies have yielded satisfactory results. The extraction efficiency has significantly improved, and feedback from domain experts indicates a relatively high level of accuracy in the extraction process. The extracted results can be used to construct a foundational knowledge graph for geoscience literature, supporting the comprehensive construction and efficient application of a geoscience knowledge graph.

A novel fine-tuning and evaluation methodology for large language models on IoT raw data summaries (LLM-RawDMeth): A joint perspective in diabetes care.

Mental health diagnoses possess unique challenges that often lead to nuanced difficulties in managing an individual’s well-being and daily functioning. Self-report questionnaires are a common practice in clinical settings to help mitigate the challenges involved in mental health disorder screening. However, these questionnaires rely on an individual’s subjective response which can be influenced by various factors. Despite the advancements of Large Language Models (LLMs), quantifying self-reported experiences with natural language processing has resulted in imperfect accuracy. This project aims to demonstrate the effectiveness of zero-shot learning LLMs for screening and assessing item scales for depression using LLMs. The DAIC-WOZ is a publicly available mental health dataset that contains textual data from clinical interviews and self-report questionnaires with relevant mental health disorder labels. The RISEN prompt engineering framework was utilized to evaluate LLMs’ effectiveness in predicting depression symptoms based on individual PHQ-8 items. Various LLMs, including GPT models, Llama3_8B, Cohere, and Gemini were assessed based on performance. The GPT models, especially GPT-4o, were consistently better than other LLMs (Llama3_8B, Cohere, Gemini) across all eight items of the PHQ-8 scale in accuracy (M = 75.9%), and F1 score (0.74). GPT models were able to predict PHQ-8 items related to emotional and cognitive states. Llama 3_8B demonstrated superior detection of anhedonia-related symptoms and the Cohere LLM’s strength was identifying and predicting psychomotor activity symptoms. This study provides a novel outlook on the potential of LLMs for predicting self-reported questionnaire scores from textual interview data. The promising preliminary performance of the various models indicates there is potential that these models could effectively assist in the screening of depression. Further research is needed to establish a framework for which LLM can be used for specific mental health symptoms and other disorders. As well, analysis of additional datasets while fine-tuning models should be explored.

Road traffic crashes (RTCs) are a global public health issue, with traditional analysis methods often hindered by delays and incomplete data. Leveraging social media for real-time traffic safety analysis offers a promising alternative, yet effective frameworks for this integration are scarce. This study introduces a novel multitask learning (MTL) framework utilizing large language models (LLMs) to analyze RTC-related tweets from Australia. We collected 26,226 traffic-related tweets from May 2022 to May 2023. Using GPT-3.5, we extracted fifteen distinct features categorized into six classification tasks and nine information retrieval tasks. These features were then used to fine-tune GPT-2 for language modeling, which outperformed baseline models, including GPT-4o mini in zero-shot mode and XGBoost, across most tasks. Unlike traditional single-task classifiers that may miss critical details, our MTL approach simultaneously classifies RTC-related tweets and extracts detailed information in natural language. Our fine-tunedGPT-2 model achieved an average accuracy of 85% across the six classification tasks, surpassing the baseline GPT-4o mini model’s 64% and XGBoost’s 83.5%. In information retrieval tasks, our fine-tuned GPT-2 model achieved a BLEU-4 score of 0.22, a ROUGE-I score of 0.78, and a WER of 0.30, significantly outperforming the baseline GPT-4 mini model’s BLEU-4 score of 0.0674, ROUGE-I score of 0.2992, and WER of 2.0715. These results demonstrate the efficacy of our fine-tuned GPT-2 model in enhancing both classification and information retrieval, offering valuable insights for data-driven decision-making to improve road safety. This study is the first to explicitly apply social media data and LLMs within an MTL framework to enhance traffic safety.

Model tuning or prompt Tuning? a study of large language models for clinical concept and relation extraction

This work aims to present an overview of using some artificial intelligence (AI) models in machine translation (MT). This work aims to integrate machine learning (ML), deep learning (DL), large language models (LLMs) to enhance machine translation between natural languages. The focus is directed to present the neural-based machine translation (NMT), and some DL models are presented. The bidirectional-encoder-representation from transformer (BERT) and LLMs are presented to utilize the big amount of textual data to learn translation patterns. The main measurable criteria that are used to evaluate the performance of MT and Arabic machine translation (AMT) are also presented. Some linguistic and technical challenges of MT and AMT are discussed. Some key points of future works in NMT are mentioned. A comparative study among some recent published related works is presented. A critical survey is presented to show the important role of DL and LLMs in MT. Some open-source toolkits, datasets and some commercial MT systems are collected and briefly presented. This work is expected to be useful for those people interested to know the up-to-date knowledge of MT and the potential role of DL and LLM in automatic translation.