Israt Jahan

Md Tahmid Rahman Laskar, Sawsan Alqahtani, M Saiful Bari et al.

Large Language Models (LLMs) have recently gained significant attention due to their remarkable capabilities in performing diverse tasks across various domains. However, a thorough evaluation of these models is crucial before deploying them in real-world applications to ensure they produce reliable performance. Despite the well-established importance of evaluating LLMs in the community, the complexity of the evaluation process has led to varied evaluation setups, causing inconsistencies in findings and interpretations. To address this, we systematically review the primary challenges and limitations causing these inconsistencies and unreliable evaluations in various steps of LLM evaluation. Based on our critical review, we present our perspectives and recommendations to ensure LLM evaluations are reproducible, reliable, and robust.

Israt Jahan, Md Tahmid Rahman Laskar, Chun Peng et al.

Recently, Large Language Models (LLM) have demonstrated impressive capability to solve a wide range of tasks. However, despite their success across various tasks, no prior work has investigated their capability in the biomedical domain yet. To this end, this paper aims to evaluate the performance of LLMs on benchmark biomedical tasks. For this purpose, we conduct a comprehensive evaluation of 4 popular LLMs in 6 diverse biomedical tasks across 26 datasets. To the best of our knowledge, this is the first work that conducts an extensive evaluation and comparison of various LLMs in the biomedical domain. Interestingly, we find based on our evaluation that in biomedical datasets that have smaller training sets, zero-shot LLMs even outperform the current state-of-the-art fine-tuned biomedical models. This suggests that pretraining on large text corpora makes LLMs quite specialized even in the biomedical domain. We also find that not a single LLM can outperform other LLMs in all tasks, with the performance of different LLMs may vary depending on the task. While their performance is still quite poor in comparison to the biomedical models that were fine-tuned on large training sets, our findings demonstrate that LLMs have the potential to be a valuable tool for various biomedical tasks that lack large annotated data.

Israt Jahan, Md Tahmid Rahman Laskar, Chun Peng et al.

ChatGPT is a large language model developed by OpenAI. Despite its impressive performance across various tasks, no prior work has investigated its capability in the biomedical domain yet. To this end, this paper aims to evaluate the performance of ChatGPT on various benchmark biomedical tasks, such as relation extraction, document classification, question answering, and summarization. To the best of our knowledge, this is the first work that conducts an extensive evaluation of ChatGPT in the biomedical domain. Interestingly, we find based on our evaluation that in biomedical datasets that have smaller training sets, zero-shot ChatGPT even outperforms the state-of-the-art fine-tuned generative transformer models, such as BioGPT and BioBART. This suggests that ChatGPT's pre-training on large text corpora makes it quite specialized even in the biomedical domain. Our findings demonstrate that ChatGPT has the potential to be a valuable tool for various tasks in the biomedical domain that lack large annotated data.

Taminul Islam, MD Alamin Hosen, Akhi Mony et al.

Recent years have seen an explosion in social media usage, allowing people to connect with others. Since the appearance of platforms such as Facebook and Twitter, such platforms influence how we speak, think, and behave. This problem negatively undermines confidence in content because of the existence of fake news. For instance, false news was a determining factor in influencing the outcome of the U.S. presidential election and other sites. Because this information is so harmful, it is essential to make sure we have the necessary tools to detect and resist it. We applied Bidirectional Long Short-Term Memory (Bi-LSTM) to determine if the news is false or real in order to showcase this study. A number of foreign websites and newspapers were used for data collection. After creating & running the model, the work achieved 84% model accuracy and 62.0 F1-macro scores with training data.

Md Tahmid Rahman Laskar, Mizanur Rahman, Israt Jahan et al.

Debatepedia is a publicly available dataset consisting of arguments and counter-arguments on controversial topics that has been widely used for the single-document query-focused abstractive summarization task in recent years. However, it has been recently found that this dataset is limited by noise and even most queries in this dataset do not have any relevance to the respective document. In this paper, we present a methodology for cleaning the Debatepedia dataset by leveraging the generative power of large language models to make it suitable for query-focused abstractive summarization. More specifically, we harness the language generation capabilities of ChatGPT to regenerate its queries. We evaluate the effectiveness of the proposed ChatGPT annotated version of the Debatepedia dataset using several benchmark summarization models and demonstrate that the newly annotated version of Debatepedia outperforms the original dataset in terms of both query relevance as well as summary generation quality. We will make this annotated and cleaned version of the dataset publicly available.

Khandoker Nosiba Arifin, Sayma Akter Rupa, Md Musfique Anwar et al.

Lemons and oranges, both are the most economically significant citrus fruits globally. The production of lemons and oranges is severely affected due to diseases in its growth stages. Fruit quality has degraded due to the presence of flaws. Thus, it is necessary to diagnose the disease accurately so that we can avoid major loss of lemons and oranges. To improve citrus farming, we proposed a disease classification approach for lemons and oranges. This approach would enable early disease detection and intervention, reduce yield losses, and optimize resource allocation. For the initial modeling of disease classification, the research uses innovative deep learning architectures such as VGG16, VGG19 and ResNet50. In addition, for achieving better accuracy, the basic machine learning algorithms used for classification problems include Random Forest, Naive Bayes, K-Nearest Neighbors (KNN) and Logistic Regression. The lemon and orange fruits diseases are classified more accurately (95.0% for lemon and 99.69% for orange) by the model. The model's base features were extracted from the ResNet50 pre-trained model and the diseases are classified by the Logistic Regression which beats the performance given by VGG16 and VGG19 for other classifiers. Experimental outcomes show that the proposed model also outperforms existing models in which most of them classified the diseases using the Softmax classifier without using any individual classifiers.

Md Tahmid Rahman Laskar, Israt Jahan, Elham Dolatabadi et al.

Large Language Models (LLMs) have demonstrated impressive performance in biomedical relation extraction, even in zero-shot scenarios. However, evaluating LLMs in this task remains challenging due to their ability to generate human-like text, often producing synonyms or abbreviations of gold-standard answers, making traditional automatic evaluation metrics unreliable. On the other hand, while human evaluation is more reliable, it is costly and time-consuming, making it impractical for real-world applications. This paper investigates the use of LLMs-as-the-Judge as an alternative evaluation method for biomedical relation extraction. We benchmark 8 LLMs as judges to evaluate the responses generated by 5 other LLMs across 3 biomedical relation extraction datasets. Unlike other text-generation tasks, we observe that LLM-based judges perform quite poorly (usually below 50% accuracy) in the biomedical relation extraction task. Our findings reveal that it happens mainly because relations extracted by LLMs do not adhere to any standard format. To address this, we propose structured output formatting for LLM-generated responses that helps LLM-Judges to improve their performance by about 15% (on average). We also introduce a domain adaptation technique to further enhance LLM-Judge performance by effectively transferring knowledge between datasets. We release both our human-annotated and LLM-annotated judgment data (36k samples in total) for public use here: https://github.com/tahmedge/llm_judge_biomedical_re.

Israt Jahan, Md Tahmid Rahman Laskar, Chun Peng et al.

This paper presents a comprehensive evaluation of cost-efficient Large Language Models (LLMs) for diverse biomedical tasks spanning both text and image modalities. We evaluated a range of closed-source and open-source LLMs on tasks such as biomedical text classification and generation, question answering, and multimodal image processing. Our experimental findings indicate that there is no single LLM that can consistently outperform others across all tasks. Instead, different LLMs excel in different tasks. While some closed-source LLMs demonstrate strong performance on specific tasks, their open-source counterparts achieve comparable results (sometimes even better), with additional benefits like faster inference and enhanced privacy. Our experimental results offer valuable insights for selecting models that are optimally suited for specific biomedical applications.

Abrar Hossain Zahin, Amit Kumar Saha, Tanvir Mridha et al.

Classifying brain tumors using magnetic resonance imaging (MRI) is crucial for early diagnosis and treatment; however, tumor heterogeneity and a dearth of annotated datasets restrict the use of supervised deep learning approaches. In this work, we use self-supervised learning (SSL) to study multi-class brain tumor classification. Using a ResNet-50 backbone, we evaluate four SSL frameworks including SimCLR, BYOL, DINO, and Moco v3 on a publicly available dataset of 4,448 MRIs with 17 distinct tumor types. On the dataset, SimCLR achieved 99.64% accuracy, 99.64% precision, 99.64% recall, and 99.64% F1-score. The workflow includes preprocessing, fine-tuning, linear evaluation, and SSL pretraining with data augmentations. Results show that, when labels are limited, SSL-pretrained models outperform supervised baselines in terms of F1-score, recall, accuracy, and precision. Additionally, by providing visual insights into model decisions, Explainable AI techniques (Grad-CAM, Grad-CAM++, EigenCAM) enhance interpretability. These results demonstrate SSL's scalability and dependability in diagnosing brain tumors from unlabeled medical data.

Israt Jahan, John S. Schreck, David John Gagne et al.

Machine learning algorithms have shown promise in reducing bias in wind gust predictions, while still underpredicting high gusts. Uncertainty quantification (UQ) supports this issue by identifying when predictions are reliable or need cautious interpretation. Using data from 61 extratropical storms in the Northeastern USA, we introduce evidential neural network (ENN) as a novel approach for UQ in gust predictions, leveraging atmospheric variables from the Weather Research and Forecasting (WRF) model. Explainable AI techniques suggested that key predictive features contributed to higher uncertainty, which correlated strongly with storm intensity and spatial gust gradients. Compared to WRF, ENN demonstrated a 47% reduction in RMSE and allowed the construction of gust prediction intervals without an ensemble, successfully capturing at least 95% of observed gusts at 179 out of 266 stations. From an operational perspective, providing gust forecasts with quantified uncertainty enhances stakeholders' confidence in risk assessment and response planning for extreme gust events.

Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Ridwan Mahbub et al.

Large Vision-Language Models (LVLMs) with only 7B parameters have shown promise as automated judges in chart comprehension tasks. However, tiny models (<=2B parameters) still perform poorly as judges, limiting their real-world use in resource-constrained settings. To address this, we propose two approaches to ensure cost-efficient evaluation: (i) multi-criteria prompting, which combines separate evaluation criteria into a single query, and (ii) domain-adaptive transfer learning, in which we fine-tune a 2B-parameter LVLM on synthetic judgments in a chart dataset to create the ChartJudge. Experiments show that multi-criteria prompting exposes robustness gaps, which led to a huge drop in performance for 7B models, including specialized LVLM judges like LLaVA-Critic. In addition, we find that our tiny LVLM (ChartJudge) can effectively transfer knowledge from one dataset to another to make it a more specialized model. Our fine-grained analysis across chart types and query complexities offers actionable insights into trade-offs between model size, prompt design, and transferability, enabling scalable, low-cost evaluation for chart reasoning tasks.

Md. Zihad Bin Jahangir, Muhammad Ashad Kabir, Sumaiya Akter et al.

Automated radiology report generation holds significant potential to reduce radiologists' workload and enhance diagnostic accuracy. However, generating precise and clinically meaningful reports from chest radiographs remains challenging due to the complexity of medical language and the need for contextual understanding. Existing models often struggle with maintaining both accuracy and contextual relevance. In this paper, we present LLaMA-XR, a novel framework that integrates LLaMA 3.1 with DenseNet-121-based image embeddings and Quantized Low-Rank Adaptation (QLoRA) fine-tuning. LLaMA-XR achieves improved coherence and clinical accuracy while maintaining computational efficiency. This efficiency is driven by an optimization strategy that enhances parameter utilization and reduces memory overhead, enabling faster report generation with lower computational resource demands. Extensive experiments conducted on the IU X-ray benchmark dataset demonstrate that LLaMA-XR outperforms a range of state-of-the-art methods. Our model achieves a ROUGE-L score of 0.433 and a METEOR score of 0.336, establishing new performance benchmarks in the domain. These results underscore LLaMA-XR's potential as an effective and efficient AI system for automated radiology reporting, offering enhanced clinical utility and reliability.