Jugal Kalita

Aaron Serianni, Jugal Kalita · mit

Neural architecture search (NAS) has allowed for the automatic creation of new and effective neural network architectures, offering an alternative to the laborious process of manually designing complex architectures. However, traditional NAS algorithms are slow and require immense amounts of computing power. Recent research has investigated training-free NAS metrics for image classification architectures, drastically speeding up search algorithms. In this paper, we investigate training-free NAS metrics for recurrent neural network (RNN) and BERT-based transformer architectures, targeted towards language modeling tasks. First, we develop a new training-free metric, named hidden covariance, that predicts the trained performance of an RNN architecture and significantly outperforms existing training-free metrics. We experimentally evaluate the effectiveness of the hidden covariance metric on the NAS-Bench-NLP benchmark. Second, we find that the current search space paradigm for transformer architectures is not optimized for training-free neural architecture search. Instead, a simple qualitative analysis can effectively shrink the search space to the best performing architectures. This conclusion is based on our investigation of existing training-free metrics and new metrics developed from recent transformer pruning literature, evaluated on our own benchmark of trained BERT architectures. Ultimately, our analysis shows that the architecture search space and the training-free metric must be developed together in order to achieve effective results.

Ahmed Bensaoud, Jugal Kalita, Mahmoud Bensaoud

The problem of malicious software (malware) detection and classification is a complex task, and there is no perfect approach. There is still a lot of work to be done. Unlike most other research areas, standard benchmarks are difficult to find for malware detection. This paper aims to investigate recent advances in malware detection on MacOS, Windows, iOS, Android, and Linux using deep learning (DL) by investigating DL in text and image classification, the use of pre-trained and multi-task learning models for malware detection approaches to obtain high accuracy and which the best approach if we have a standard benchmark dataset. We discuss the issues and the challenges in malware detection using DL classifiers by reviewing the effectiveness of these DL classifiers and their inability to explain their decisions and actions to DL developers presenting the need to use Explainable Machine Learning (XAI) or Interpretable Machine Learning (IML) programs. Additionally, we discuss the impact of adversarial attacks on deep learning models, negatively affecting their generalization capabilities and resulting in poor performance on unseen data. We believe there is a need to train and test the effectiveness and efficiency of the current state-of-the-art deep learning models on different malware datasets. We examine eight popular DL approaches on various datasets. This survey will help researchers develop a general understanding of malware recognition using deep learning.

Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita

Manually constructing a Wordnet is a difficult task, needing years of experts' time. As a first step to automatically construct full Wordnets, we propose approaches to generate Wordnet synsets for languages both resource-rich and resource-poor, using publicly available Wordnets, a machine translator and/or a single bilingual dictionary. Our algorithms translate synsets of existing Wordnets to a target language T, then apply a ranking method on the translation candidates to find best translations in T. Our approaches are applicable to any language which has at least one existing bilingual dictionary translating from English to it.

Khang Nhut Lam, Nguyen Hoang Huynh, Nguyen Bao Ngoc et al.

The research reported in this paper transforms a normal trash bin into a smarter one by applying computer vision technology. With the support of sensors and actuator devices, the trash bin can automatically classify garbage. In particular, a camera on the trash bin takes pictures of trash, then the central processing unit analyzes and makes decisions regarding which bin to drop trash into. The accuracy of our trash bin system achieves 90%. Besides, our model is connected to the Internet to update the bin status for further management. A mobile application is developed for managing the bin.

Khang Nhut Lam, Jugal Kalita

Bilingual dictionaries are expensive resources and not many are available when one of the languages is resource-poor. In this paper, we propose algorithms for creation of new reverse bilingual dictionaries from existing bilingual dictionaries in which English is one of the two languages. Our algorithms exploit the similarity between word-concept pairs using the English Wordnet to produce reverse dictionary entries. Since our algorithms rely on available bilingual dictionaries, they are applicable to any bilingual dictionary as long as one of the two languages has Wordnet type lexical ontology.

Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita

This paper proposes approaches to automatically create a large number of new bilingual dictionaries for low-resource languages, especially resource-poor and endangered languages, from a single input bilingual dictionary. Our algorithms produce translations of words in a source language to plentiful target languages using available Wordnets and a machine translator (MT). Since our approaches rely on just one input dictionary, available Wordnets and an MT, they are applicable to any bilingual dictionary as long as one of the two languages is English or has a Wordnet linked to the Princeton Wordnet. Starting with 5 available bilingual dictionaries, we create 48 new bilingual dictionaries. Of these, 30 pairs of languages are not supported by the popular MTs: Google and Bing.

Melkamu Mersha, Khang Lam, Joseph Wood et al.

Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these challenges by providing explanations for how these models make decisions and predictions, ensuring transparency, accountability, and fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, and the scope of XAI techniques. However, there remains a gap in the literature as there are no comprehensive reviews that delve into the detailed mathematical representations, design methodologies of XAI models, and other associated aspects. This paper provides a comprehensive literature review encompassing common terminologies and definitions, the need for XAI, beneficiaries of XAI, a taxonomy of XAI methods, and the application of XAI methods in different application areas. The survey is aimed at XAI researchers, XAI practitioners, AI model developers, and XAI beneficiaries who are interested in enhancing the trustworthiness, transparency, accountability, and fairness of their AI models.

Gabriel Mantione-Holmes, Justin Leo, Jugal Kalita

In order for artificial neural networks to begin accurately mimicking biological ones, they must be able to adapt to new exigencies without forgetting what they have learned from previous training. Lifelong learning approaches to artificial neural networks attempt to strive towards this goal, yet have not progressed far enough to be realistically deployed for natural language processing tasks. The proverbial roadblock of catastrophic forgetting still gate-keeps researchers from an adequate lifelong learning model. While efforts are being made to quell catastrophic forgetting, there is a lack of research that looks into the importance of class ordering when training on new classes for incremental learning. This is surprising as the ordering of "classes" that humans learn is heavily monitored and incredibly important. While heuristics to develop an ideal class order have been researched, this paper examines class ordering as it relates to priming as a scheme for incremental class learning. By examining the connections between various methods of priming found in humans and how those are mimicked yet remain unexplained in life-long machine learning, this paper provides a better understanding of the similarities between our biological systems and the synthetic systems while simultaneously improving current practices to combat catastrophic forgetting. Through the merging of psychological priming practices with class ordering, this paper is able to identify a generalizable method for class ordering in NLP incremental learning tasks that consistently outperforms random class ordering.

Khang Nhut Lam, Kim-Ngoc Thi Nguyen, Loc Huu Nguy et al.

This paper discusses a facial expression recognition model and a description generation model to build descriptive sentences for images and facial expressions of people in images. Our study shows that YOLOv5 achieves better results than a traditional CNN for all emotions on the KDEF dataset. In particular, the accuracies of the CNN and YOLOv5 models for emotion recognition are 0.853 and 0.938, respectively. A model for generating descriptions for images based on a merged architecture is proposed using VGG16 with the descriptions encoded over an LSTM model. YOLOv5 is also used to recognize dominant colors of objects in the images and correct the color words in the descriptions generated if it is necessary. If the description contains words referring to a person, we recognize the emotion of the person in the image. Finally, we combine the results of all models to create sentences that describe the visual content and the human emotions in the images. Experimental results on the Flickr8k dataset in Vietnamese achieve BLEU-1, BLEU-2, BLEU-3, BLEU-4 scores of 0.628; 0.425; 0.280; and 0.174, respectively.

Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita

This paper examines approaches to generate lexical resources for endangered languages. Our algorithms construct bilingual dictionaries and multilingual thesauruses using public Wordnets and a machine translator (MT). Since our work relies on only one bilingual dictionary between an endangered language and an "intermediate helper" language, it is applicable to languages that lack many existing resources.

Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita

Past approaches to translate a phrase in a language L1 to a language L2 using a dictionary-based approach require grammar rules to restructure initial translations. This paper introduces a novel method without using any grammar rules to translate a given phrase in L1, which does not exist in the dictionary, to L2. We require at least one L1-L2 bilingual dictionary and n-gram data in L2. The average manual evaluation score of our translations is 4.29/5.00, which implies very high quality.

Abby Newcomb, Jugal Kalita

Automated math word problem solvers based on neural networks have successfully managed to obtain 70-80\% accuracy in solving arithmetic word problems. However, it has been shown that these solvers may rely on superficial patterns to obtain their equations. In order to determine what information math word problem solvers use to generate solutions, we remove parts of the input and measure the model's performance on the perturbed dataset. Our results show that the model is not sensitive to the removal of many words from the input and can still manage to find a correct answer when given a nonsense question. This indicates that automatic solvers do not follow the semantic logic of math word problems, and may be overfitting to the presence of specific words.

Hassan Shakil, Ahmad Farooq, Jugal Kalita

Specifically focusing on the landscape of abstractive text summarization, as opposed to extractive techniques, this survey presents a comprehensive overview, delving into state-of-the-art techniques, prevailing challenges, and prospective research directions. We categorize the techniques into traditional sequence-to-sequence models, pre-trained large language models, reinforcement learning, hierarchical methods, and multi-modal summarization. Unlike prior works that did not examine complexities, scalability and comparisons of techniques in detail, this review takes a comprehensive approach encompassing state-of-the-art methods, challenges, solutions, comparisons, limitations and charts out future improvements - providing researchers an extensive overview to advance abstractive summarization research. We provide vital comparison tables across techniques categorized - offering insights into model complexity, scalability and appropriate applications. The paper highlights challenges such as inadequate meaning representation, factual consistency, controllable text summarization, cross-lingual summarization, and evaluation metrics, among others. Solutions leveraging knowledge incorporation and other innovative strategies are proposed to address these challenges. The paper concludes by highlighting emerging research areas like factual inconsistency, domain-specific, cross-lingual, multilingual, and long-document summarization, as well as handling noisy data. Our objective is to provide researchers and practitioners with a structured overview of the domain, enabling them to better understand the current landscape and identify potential areas for further research and improvement.

Dan DeGenaro, Jugal Kalita

Large language models having hundreds of millions, and even billions, of parameters have performed extremely well on a variety of natural language processing (NLP) tasks. Their widespread use and adoption, however, is hindered by the lack of availability and portability of sufficiently large computational resources. This paper proposes a knowledge distillation (KD) technique building on the work of LightMBERT, a student model of multilingual BERT (mBERT). By repeatedly distilling mBERT through increasingly compressed toplayer distilled teacher assistant networks, CAMeMBERT aims to improve upon the time and space complexities of mBERT while keeping loss of accuracy beneath an acceptable threshold. At present, CAMeMBERT has an average accuracy of around 60.1%, which is subject to change after future improvements to the hyperparameters used in fine-tuning.

Melkamu Abay Mersha, Mesay Gemeda yigezu, Jugal Kalita

Topic modeling is a powerful technique to discover hidden topics and patterns within a collection of documents without prior knowledge. Traditional topic modeling and clustering-based techniques encounter challenges in capturing contextual semantic information. This study introduces an innovative end-to-end semantic-driven topic modeling technique for the topic extraction process, utilizing advanced word and document embeddings combined with a powerful clustering algorithm. This semantic-driven approach represents a significant advancement in topic modeling methodologies. It leverages contextual semantic information to extract coherent and meaningful topics. Specifically, our model generates document embeddings using pre-trained transformer-based language models, reduces the dimensions of the embeddings, clusters the embeddings based on semantic similarity, and generates coherent topics for each cluster. Compared to ChatGPT and traditional topic modeling algorithms, our model provides more coherent and meaningful topics.

Hellina Hailu Nigatu, Atnafu Lambebo Tonja, Jugal Kalita

Multilingual Language Models offer a way to incorporate multiple languages in one model and utilize cross-language transfer learning to improve performance for different Natural Language Processing (NLP) tasks. Despite progress in multilingual models, not all languages are supported as well, particularly in low-resource settings. In this work, we investigate the linguistic representation of different languages in multilingual models. We start by asking the question which languages are supported in popular multilingual models and which languages are left behind. Then, for included languages, we look at models' learned representations based on language family and dialect and try to understand how models' learned representations for~(1) seen and~(2) unseen languages vary across different language groups. In addition, we test and analyze performance on downstream tasks such as text generation and Named Entity Recognition. We observe from our experiments that community-centered models -- models that focus on languages of a given family or geographical location and are built by communities who speak them -- perform better at distinguishing between languages in the same family for low-resource languages. Our paper contributes to the literature in understanding multilingual models and their shortcomings and offers insights on potential ways to improve them.

Melkamu Abay Mersha, Jugal Kalita

Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions, capture either local token-level attributions or global attention patterns without unification, and lack context-awareness of inter-token dependencies and structural components. They also fail to capture how relevance evolves across layers and how structural components shape decision-making. To address these limitations, we proposed the \textbf{Context-Aware Layer-wise Integrated Gradients (CA-LIG) Framework}, a unified hierarchical attribution framework that computes layer-wise Integrated Gradients within each Transformer block and fuses these token-level attributions with class-specific attention gradients. This integration yields signed, context-sensitive attribution maps that capture supportive and opposing evidence while tracing the hierarchical flow of relevance through the Transformer layers. We evaluate the CA-LIG Framework across diverse tasks, domains, and transformer model families, including sentiment analysis and long and multi-class document classification with BERT, hate speech detection in a low-resource language setting with XLM-R and AfroLM, and image classification with Masked Autoencoder vision Transformer model. Across all tasks and architectures, CA-LIG provides more faithful attributions, shows stronger sensitivity to contextual dependencies, and produces clearer, more semantically coherent visualizations than established explainability methods. These results indicate that CA-LIG provides a more comprehensive, context-aware, and reliable explanation of Transformer decision-making, advancing both the practical interpretability and conceptual understanding of deep neural models.

Tianshuo Yang, Ryan Rabinowitz, Terrance E. Boult et al.

Transformer classifiers such as BERT deliver impressive closed-set accuracy, yet they remain brittle when confronted with inputs from unseen categories--a common scenario for deployed NLP systems. We investigate Open-Set Recognition (OSR) for text by porting the feature attenuation hypothesis from computer vision to transformers and by benchmarking it against state-of-the-art baselines. Concretely, we adapt the COSTARR framework--originally designed for classification in computer vision--to two modest language models (BERT (base) and GPT-2) trained to label 176 arXiv subject areas. Alongside COSTARR, we evaluate Maximum Softmax Probability (MSP), MaxLogit, and the temperature-scaled free-energy score under the OOSA and AUOSCR metrics. Our results show (i) COSTARR extends to NLP without retraining but yields no statistically significant gain over MaxLogit or MSP, and (ii) free-energy lags behind all other scores in this high-class-count setting. The study highlights both the promise and the current limitations of transplanting vision-centric OSR ideas to language models, and points toward the need for larger backbones and task-tailored attenuation strategies.

Akshat Ghiya, Ali K. AlShami, Jugal Kalita

Predicting pedestrian trajectories is essential for autonomous driving systems, as it significantly enhances safety and supports informed decision-making. Accurate predictions enable the prevention of collisions, anticipation of crossing intent, and improved overall system efficiency. In this study, we present SGNetPose+, an enhancement of the SGNet architecture designed to integrate skeleton information or body segment angles with bounding boxes to predict pedestrian trajectories from video data to avoid hazards in autonomous driving. Skeleton information was extracted using a pose estimation model, and joint angles were computed based on the extracted joint data. We also apply temporal data augmentation by horizontally flipping video frames to increase the dataset size and improve performance. Our approach achieves state-of-the-art results on the JAAD and PIE datasets using pose data with the bounding boxes, outperforming the SGNet model. Code is available on Github: SGNetPose+.

Wes Robbins, Zanyar Zohourianshahzadi, Jugal Kalita

Vision-language models can assess visual context in an image and generate descriptive text. While the generated text may be accurate and syntactically correct, it is often overly general. To address this, recent work has used optical character recognition to supplement visual information with text extracted from an image. In this work, we contend that vision-language models can benefit from additional information that can be extracted from an image, but are not used by current models. We modify previous multimodal frameworks to accept relevant information from any number of auxiliary classifiers. In particular, we focus on person names as an additional set of tokens and create a novel image-caption dataset to facilitate captioning with person names. The dataset, Politicians and Athletes in Captions (PAC), consists of captioned images of well-known people in context. By fine-tuning pretrained models with this dataset, we demonstrate a model that can naturally integrate facial recognition tokens into generated text by training on limited data. For the PAC dataset, we provide a discussion on collection and baseline benchmark scores.

Harrison Gietz, Jugal Kalita

The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diffusion models has proven useful for purifying input images, thus improving model robustness against adversarial attacks. Similarly, some initial work has explored the use of random noising and de-noising to mitigate adversarial attacks in an NLP setting, but improving the quality and efficiency of these methods is necessary for them to remain competitive. We extend upon methods of input text purification that are inspired by diffusion processes, which randomly mask and refill portions of the input text before classification. Our novel method, MaskPure, exceeds or matches robustness compared to other contemporary defenses, while also requiring no adversarial classifier training and without assuming knowledge of the attack type. In addition, we show that MaskPure is provably certifiably robust. To our knowledge, MaskPure is the first stochastic-purification method with demonstrated success against both character-level and word-level attacks, indicating the generalizable and promising nature of stochastic denoising defenses. In summary: the MaskPure algorithm bridges literature on the current strongest certifiable and empirical adversarial defense methods, showing that both theoretical and practical robustness can be obtained together. Code is available on GitHub at https://github.com/hubarruby/MaskPure.

Ahmed Bensaoud, Jugal Kalita

In this paper, we propose a novel model for a malware classification system based on Application Programming Interface (API) calls and opcodes, to improve classification accuracy. This system uses a novel design of combined Convolutional Neural Network and Long Short-Term Memory. We extract opcode sequences and API Calls from Windows malware samples for classification. We transform these features into N-grams (N = 2, 3, and 10)-gram sequences. Our experiments on a dataset of 9,749,57 samples produce high accuracy of 99.91% using the 8-gram sequences. Our method significantly improves the malware classification performance when using a wide range of recent deep learning architectures, leading to state-of-the-art performance. In particular, we experiment with ConvNeXt-T, ConvNeXt-S, RegNetY-4GF, RegNetY-8GF, RegNetY-12GF, EfficientNetV2, Sequencer2D-L, Swin-T, ViT-G/14, ViT-Ti, ViT-S, VIT-B, VIT-L, and MaxViT-B. Among these architectures, Swin-T and Sequencer2D-L architectures achieved high accuracies of 99.82% and 99.70%, respectively, comparable to our CNN-LSTM architecture although not surpassing it.

Ali K. AlShami, Terrance Boult, Jugal Kalita

Tracking the trajectory of tennis players can help camera operators in production. Predicting future movement enables cameras to automatically track and predict a player's future trajectory without human intervention. Predicting future human movement in the context of complex physical tasks is also intellectually satisfying. Swift advancements in sports analytics and the wide availability of videos for tennis have inspired us to propose a novel method called Pose2Trajectory, which predicts a tennis player's future trajectory as a sequence derived from their body joints' data and ball position. Demonstrating impressive accuracy, our approach capitalizes on body joint information to provide a comprehensive understanding of the human body's geometry and motion, thereby enhancing the prediction of the player's trajectory. We use encoder-decoder Transformer architecture trained on the joints and trajectory information of the players with ball positions. The predicted sequence can provide information to help close-up cameras to keep tracking the tennis player, following centroid coordinates. We generate a high-quality dataset from multiple videos to assist tennis player movement prediction using object detection and human pose estimation methods. It contains bounding boxes and joint information for tennis players and ball positions in singles tennis games. Our method shows promising results in predicting the tennis player's movement trajectory with different sequence prediction lengths using the joints and trajectory information with the ball position.

Ali K. AlShami, Ryan Rabinowitz, Khang Lam et al.

Human Action Recognition (HAR) is a challenging domain in computer vision, involving recognizing complex patterns by analyzing the spatiotemporal dynamics of individuals' movements in videos. These patterns arise in sequential data, such as video frames, which are often essential to accurately distinguish actions that would be ambiguous in a single image. HAR has garnered considerable interest due to its broad applicability, ranging from robotics and surveillance systems to sports motion analysis, healthcare, and the burgeoning field of autonomous vehicles. While several taxonomies have been proposed to categorize HAR approaches in surveys, they often overlook hybrid methodologies and fail to demonstrate how different models incorporate various architectures and modalities. In this comprehensive survey, we present the novel SMART-Vision taxonomy, which illustrates how innovations in deep learning for HAR complement one another, leading to hybrid approaches beyond traditional categories. Our survey provides a clear roadmap from foundational HAR works to current state-of-the-art systems, highlighting emerging research directions and addressing unresolved challenges in discussion sections for architectures within the HAR domain. We provide details of the research datasets that various approaches used to measure and compare goodness HAR approaches. We also explore the rapidly emerging field of Open-HAR systems, which challenges HAR systems by presenting samples from unknown, novel classes during test time.

Ahmed Bensaoud, Jugal Kalita

The rapid expansion of Internet of Things (IoT) devices has increased the risk of cyber-attacks, making effective detection essential for securing IoT networks. This work introduces a novel approach combining Self-Organizing Maps (SOMs), Deep Belief Networks (DBNs), and Autoencoders to detect known and previously unseen attack patterns. A comprehensive evaluation using simulated and real-world traffic data is conducted, with models optimized via Particle Swarm Optimization (PSO). The system achieves an accuracy of up to 99.99% and Matthews Correlation Coefficient (MCC) values exceeding 99.50%. Experiments on NSL-KDD, UNSW-NB15, and CICIoT2023 confirm the model's strong performance across diverse attack types. These findings suggest that the proposed method enhances IoT security by identifying emerging threats and adapting to evolving attack strategies.

Melkamu Abay Mersha, Mesay Gemeda Yigezu, Jugal Kalita

The black-box nature of large language models (LLMs) necessitates the development of eXplainable AI (XAI) techniques for transparency and trustworthiness. However, evaluating these techniques remains a challenge. This study presents a general evaluation framework using four key metrics: Human-reasoning Agreement (HA), Robustness, Consistency, and Contrastivity. We assess the effectiveness of six explainability techniques from five different XAI categories model simplification (LIME), perturbation-based methods (SHAP), gradient-based approaches (InputXGradient, Grad-CAM), Layer-wise Relevance Propagation (LRP), and attention mechanisms-based explainability methods (Attention Mechanism Visualization, AMV) across five encoder-based language models: TinyBERT, BERTbase, BERTlarge, XLM-R large, and DeBERTa-xlarge, using the IMDB Movie Reviews and Tweet Sentiment Extraction (TSE) datasets. Our findings show that the model simplification-based XAI method (LIME) consistently outperforms across multiple metrics and models, significantly excelling in HA with a score of 0.9685 on DeBERTa-xlarge, robustness, and consistency as the complexity of large language models increases. AMV demonstrates the best Robustness, with scores as low as 0.0020. It also excels in Consistency, achieving near-perfect scores of 0.9999 across all models. Regarding Contrastivity, LRP performs the best, particularly on more complex models, with scores up to 0.9371.

Ali K. AlShami, Ananya Kalita, Ryan Rabinowitz et al.

As the Computer Vision community rapidly develops and advances algorithms for autonomous driving systems, the goal of safer and more efficient autonomous transportation is becoming increasingly achievable. However, it is 2024, and we still do not have fully self-driving cars. One of the remaining core challenges lies in addressing the novelty problem, where self-driving systems still struggle to handle previously unseen situations on the open road. With our Challenge of Out-Of-Label (COOOL) benchmark, we introduce a novel dataset for hazard detection, offering versatile evaluation metrics applicable across various tasks, including novelty-adjacent domains such as Anomaly Detection, Open-Set Recognition, Open Vocabulary, and Domain Adaptation. COOOL comprises over 200 collections of dashcam-oriented videos, annotated by human labelers to identify objects of interest and potential driving hazards. It includes a diverse range of hazards and nuisance objects. Due to the dataset's size and data complexity, COOOL serves exclusively as an evaluation benchmark.

Melkamu Mersha, Mingiziem Bitewa, Tsion Abay et al.

Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation techniques like Local Interpretable Model-Agnostic Explanations (LIME) have emerged as essential tools for providing insights into the behavior of these complex systems. This study leverages LIME to interpret a multi-layer perceptron (MLP) neural network trained on a text classification task. By analyzing the contribution of individual features to model predictions, the LIME approach enhances interpretability and supports informed decision-making. Despite its effectiveness in offering localized explanations, LIME has limitations in capturing global patterns and feature interactions. This research highlights the strengths and shortcomings of LIME and proposes directions for future work to achieve more comprehensive interpretability in neural NLP models.

Melkamu Abay Mersha, Mesay Gemeda Yigezu, Atnafu Lambebo Tonja et al.

Explainable AI (XAI) has emerged as a powerful tool for improving the performance of AI models, going beyond providing model transparency and interpretability. The scarcity of labeled data remains a fundamental challenge in developing robust and generalizable AI models, particularly for low-resource languages. Conventional data augmentation techniques introduce noise, cause semantic drift, disrupt contextual coherence, lack control, and lead to overfitting. To address these challenges, we propose XAI-Guided Context-Aware Data Augmentation. This novel framework leverages XAI techniques to modify less critical features while selectively preserving most task-relevant features. Our approach integrates an iterative feedback loop, which refines augmented data over multiple augmentation cycles based on explainability-driven insights and the model performance gain. Our experimental results demonstrate that XAI-SR-BT and XAI-PR-BT improve the accuracy of models on hate speech and sentiment analysis tasks by 6.6% and 8.1%, respectively, compared to the baseline, using the Amharic dataset with the XLM-R model. XAI-SR-BT and XAI-PR-BT outperform existing augmentation techniques by 4.8% and 5%, respectively, on the same dataset and model. Overall, XAI-SR-BT and XAI-PR-BT consistently outperform both baseline and conventional augmentation techniques across all tasks and models. This study provides a more controlled, interpretable, and context-aware solution to data augmentation, addressing critical limitations of existing augmentation techniques and offering a new paradigm shift for leveraging XAI techniques to enhance AI model training.

Atnafu Lambebo Tonja, Melkamu Mersha, Ananya Kalita et al.

This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of languages from across the world.

Atnafu Lambebo Tonja, Olga Kolesnikova, Alexander Gelbukh et al.

Recent research in natural language processing (NLP) has achieved impressive performance in tasks such as machine translation (MT), news classification, and question-answering in high-resource languages. However, the performance of MT leaves much to be desired for low-resource languages. This is due to the smaller size of available parallel corpora in these languages, if such corpora are available at all. NLP in Ethiopian languages suffers from the same issues due to the unavailability of publicly accessible datasets for NLP tasks, including MT. To help the research community and foster research for Ethiopian languages, we introduce EthioMT -- a new parallel corpus for 15 languages. We also create a new benchmark by collecting a dataset for better-researched languages in Ethiopia. We evaluate the newly collected corpus and the benchmark dataset for 23 Ethiopian languages using transformer and fine-tuning approaches.

Joshua Zingale, Jugal Kalita

Controlled text generation (CTG) seeks to guide large language model (LLM) output to produce text that conforms to desired criteria. The current study presents a novel CTG algorithm that enforces adherence toward specific rhetorical relations in an LLM sentence-completion context by a parser-driven decoding scheme that requires no model fine-tuning. The method is validated both with automatic and human evaluation. The code is accessible on GitHub.

Logan Golia, Jugal Kalita

The increased prevalence of online meetings has significantly enhanced the practicality of a model that can automatically generate the summary of a given meeting. This paper introduces a novel and effective approach to automate the generation of meeting summaries. Current approaches to this problem generate general and basic summaries, considering the meeting simply as a long dialogue. However, our novel algorithms can generate abstractive meeting summaries that are driven by the action items contained in the meeting transcript. This is done by recursively generating summaries and employing our action-item extraction algorithm for each section of the meeting in parallel. All of these sectional summaries are then combined and summarized together to create a coherent and action-item-driven summary. In addition, this paper introduces three novel methods for dividing up long transcripts into topic-based sections to improve the time efficiency of our algorithm, as well as to resolve the issue of large language models (LLMs) forgetting long-term dependencies. Our pipeline achieved a BERTScore of 64.98 across the AMI corpus, which is an approximately 4.98% increase from the current state-of-the-art result produced by a fine-tuned BART (Bidirectional and Auto-Regressive Transformers) model.

Smita Khapre, Melkamu Abay Mersha, Hassan Shakil et al.

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

Mitchell Piehl, Dillon Wilson, Ananya Kalita et al.

Large Language Models (LLMs) excel at various tasks, including problem-solving and question-answering. However, LLMs often find Math Word Problems (MWPs) challenging because solving them requires a range of reasoning and mathematical abilities with which LLMs seem to struggle. Recent efforts have helped LLMs solve more complex MWPs with improved prompts. This study proposes a novel method that initially prompts an LLM to create equations from a decomposition of the question, followed by using an external symbolic equation solver to produce an answer. To ensure the accuracy of the obtained answer, inspired by an established recommendation of math teachers, the LLM is instructed to solve the MWP a second time, but this time with the objective of estimating the correct answer instead of solving it exactly. The estimation is then compared to the generated answer to verify. If verification fails, an iterative rectification process is employed to ensure the correct answer is eventually found. This approach achieves new state-of-the-art results on datasets used by prior published research on numeric and algebraic MWPs, improving the previous best results by nearly two percent on average. In addition, the approach obtains satisfactory results on trigonometric MWPs, a task not previously attempted to the authors' best knowledge. This study also introduces two new datasets, SVAMPClean and Trig300, to further advance the testing of LLMs' reasoning abilities.

Melkamu Abay Mersha, Jugal Kalita

Virtual brainstorming sessions have become a central component of collaborative problem solving, yet the large volume and uneven distribution of ideas often make it difficult to extract valuable insights efficiently. Manual coding of ideas is time-consuming and subjective, underscoring the need for automated approaches to support the evaluation of group creativity. In this study, we propose a semantic-driven topic modeling framework that integrates four modular components: transformer-based embeddings (Sentence-BERT), dimensionality reduction (UMAP), clustering (HDBSCAN), and topic extraction with refinement. The framework captures semantic similarity at the sentence level, enabling the discovery of coherent themes from brainstorming transcripts while filtering noise and identifying outliers. We evaluate our approach on structured Zoom brainstorming sessions involving student groups tasked with improving their university. Results demonstrate that our model achieves higher topic coherence compared to established methods such as LDA, ETM, and BERTopic, with an average coherence score of 0.687 (CV), outperforming baselines by a significant margin. Beyond improved performance, the model provides interpretable insights into the depth and diversity of topics explored, supporting both convergent and divergent dimensions of group creativity. This work highlights the potential of embedding-based topic modeling for analyzing collaborative ideation and contributes an efficient and scalable framework for studying creativity in synchronous virtual meetings.

Luke Delzer, Robert Kroleski, Ali K. AlShami et al.

Drug repurposing has historically been an economically infeasible process for identifying novel uses for abandoned drugs. Modern machine learning has enabled the identification of complex biochemical intricacies in candidate drugs; however, many studies rely on simplified datasets with known drug-disease similarities. We propose a machine learning pipeline that uses unsupervised deep embedded clustering, combined with supervised graph neural network link prediction to identify new drug-disease links from multi-omic data. Unsupervised autoencoder and cluster training reduced the dimensionality of omic data into a compressed latent embedding. A total of 9,022 unique drugs were partitioned into 35 clusters with a mean silhouette score of 0.8550. Graph neural networks achieved strong statistical performance, with a prediction accuracy of 0.901, receiver operating characteristic area under the curve of 0.960, and F1-Score of 0.901. A ranked list comprised of 477 per-cluster link probabilities exceeding 99 percent was generated. This study could provide new drug-disease link prospects across unrelated disease domains, while advancing the understanding of machine learning in drug repurposing studies.

Ali K. AlShami, Ryan Rabinowitz, Maged Shoman et al.

As the computer vision community advances autonomous driving algorithms, integrating vision-based insights with sensor data remains essential for improving perception, decision making, planning, prediction, simulation, and control. Yet we must ask: Why don't we have entirely safe self-driving cars yet? A key part of the answer lies in addressing novel scenarios, one of the most critical barriers to real-world deployment. Our 2COOOL workshop provides a dedicated forum for researchers and industry experts to push the state of the art in novelty handling, including out-of-distribution hazard detection, vision-language models for hazard understanding, new benchmarking and methodologies, and safe autonomous driving practices. The 2nd Workshop on the Challenge of Out-of-Label Hazards in Autonomous Driving (2COOOL) will be held at the International Conference on Computer Vision (ICCV) 2025 in Honolulu, Hawaii, on October 19, 2025. We aim to inspire the development of new algorithms and systems for hazard avoidance, drawing on ideas from anomaly detection, open-set recognition, open-vocabulary modeling, domain adaptation, and related fields. Building on the success of its inaugural edition at the Winter Conference on Applications of Computer Vision (WACV) 2025, the workshop will feature a mix of academic and industry participation.

Eric Xia, Jugal Kalita

A two-part affine approximation has been found to be a good approximation for transformer computations over certain subject object relations. Adapting the Bigger Analogy Test Set, we show that the linear transformation Ws, where s is a middle layer representation of a subject token and W is derived from model derivatives, is also able to accurately reproduce final object states for many relations. This linear technique is able to achieve 90% faithfulness on morphological relations, and we show similar findings multi-lingually and across models. Our findings indicate that some conceptual relationships in language models, such as morphology, are readily interpretable from latent space, and are sparsely encoded by cross-layer linear transformations.

Ahmed Bensaoud, Jugal Kalita

Active learning for classification seeks to reduce the cost of labeling samples by finding unlabeled examples about which the current model is least certain and sending them to an annotator/expert to label. Bayesian theory can provide a probabilistic view of deep neural network models by asserting a prior distribution over model parameters and estimating the uncertainties by posterior distribution over these parameters. This paper proposes two novel active learning approaches to label one million malware examples belonging to different unknown modern malware families. The first model is Inception-V4+PCA combined with several support vector machine (SVM) algorithms (UTSVM, PSVM, SVM-GSU, TBSVM). The second model is Vision Transformer based Bayesian Neural Networks ViT-BNN. Our proposed ViT-BNN is a state-of-the-art active learning approach that differs from current methods and can apply to any particular task. The experiments demonstrate that the ViT-BNN is more stable and robust in handling uncertainty.

Ahmed Bensaoud, Jugal Kalita

Malicious software is a pernicious global problem. A novel multi-task learning framework is proposed in this paper for malware image classification for accurate and fast malware detection. We generate bitmap (BMP) and (PNG) images from malware features, which we feed to a deep learning classifier. Our state-of-the-art multi-task learning approach has been tested on a new dataset, for which we have collected approximately 100,000 benign and malicious PE, APK, Mach-o, and ELF examples. Experiments with seven tasks tested with 4 activation functions, ReLU, LeakyReLU, PReLU, and ELU separately demonstrate that PReLU gives the highest accuracy of more than 99.87% on all tasks. Our model can effectively detect a variety of obfuscation methods like packing, encryption, and instruction overlapping, strengthing the beneficial claims of our model, in addition to achieving the state-of-art methods in terms of accuracy.

Atnafu Lambebo Tonja, Hellina Hailu Nigatu, Olga Kolesnikova et al.

This paper describes CIC NLP's submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas. We present the system descriptions for three methods. We used two multilingual models, namely M2M-100 and mBART50, and one bilingual (one-to-one) -- Helsinki NLP Spanish-English translation model, and experimented with different transfer learning setups. We experimented with 11 languages from America and report the setups we used as well as the results we achieved. Overall, the mBART setup was able to improve upon the baseline for three out of the eleven languages.

Khang Nhut Lam, Thieu Gia Doan, Khang Thua Pham et al.

Summary sentences produced by abstractive summarization models may be coherent and comprehensive, but they lack control and rely heavily on reference summaries. The BRIO training paradigm assumes a non-deterministic distribution to reduce the model's dependence on reference summaries, and improve model performance during inference. This paper presents a straightforward but effective technique to improve abstractive summaries by fine-tuning pre-trained language models, and training them with the BRIO paradigm. We build a text summarization dataset for Vietnamese, called VieSum. We perform experiments with abstractive summarization models trained with the BRIO paradigm on the CNNDM and the VieSum datasets. The results show that the models, trained on basic hardware, outperform all existing abstractive summarization models, especially for Vietnamese.

Daniel Boyle, Jugal Kalita

Financial markets are an intriguing place that offer investors the potential to gain large profits if timed correctly. Unfortunately, the dynamic, non-linear nature of financial markets makes it extremely hard to predict future price movements. Within the US stock exchange, there are a countless number of factors that play a role in the price of a company's stock, including but not limited to financial statements, social and news sentiment, overall market sentiment, political happenings and trading psychology. Correlating these factors is virtually impossible for a human. Therefore, we propose STST, a novel approach using a Spatiotemporal Transformer-LSTM model for stock movement prediction. Our model obtains accuracies of 63.707 and 56.879 percent against the ACL18 and KDD17 datasets, respectively. In addition, our model was used in simulation to determine its real-life applicability. It obtained a minimum of 10.41% higher profit than the S&P500 stock index, with a minimum annualized return of 31.24%.

Abigail Swenor, Jugal Kalita

Attacks on deep learning models are often difficult to identify and therefore are difficult to protect against. This problem is exacerbated by the use of public datasets that typically are not manually inspected before use. In this paper, we offer a solution to this vulnerability by using, during testing, random perturbations such as spelling correction if necessary, substitution by random synonym, or simply dropping the word. These perturbations are applied to random words in random sentences to defend NLP models against adversarial attacks. Our Random Perturbations Defense and Increased Randomness Defense methods are successful in returning attacked models to similar accuracy of models before attacks. The original accuracy of the model used in this work is 80% for sentiment classification. After undergoing attacks, the accuracy drops to accuracy between 0% and 44%. After applying our defense methods, the accuracy of the model is returned to the original accuracy within statistical significance.

Justin Leo, Jugal Kalita

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt to develop a more realistic model, the concept of working in an open set environment has been introduced. This in turn leads to the concept of incremental learning where a model with its own architecture and initial trained set of data can identify unknown classes during the testing phase and autonomously update itself if evidence of a new class is detected. Some problems that arise in incremental learning are inefficient use of resources to retrain the classifier repeatedly and the decrease of classification accuracy as multiple classes are added over time. This process of instantiating new classes is repeated as many times as necessary, accruing errors. To address these problems, this paper proposes the Classification Confidence Threshold approach to prime neural networks for incremental learning to keep accuracies high by limiting forgetting. A lean method is also used to reduce resources used in the retraining of the neural network. The proposed method is based on the idea that a network is able to incrementally learn a new class even when exposed to a limited number samples associated with the new class. This method can be applied to most existing neural networks with minimal changes to network architecture.

Thomas Conley, Jack St. Clair, Jugal Kalita

Although people have the ability to engage in vapid dialogue without effort, this may not be a uniquely human trait. Since the 1960's researchers have been trying to create agents that can generate artificial conversation. These programs are commonly known as chatbots. With increasing use of neural networks for dialog generation, some conclude that this goal has been achieved. This research joins the quest by creating a dialog generating Recurrent Neural Network (RNN) and by enhancing the ability of this network with auxiliary loss functions and a beam search. Our custom loss functions achieve better cohesion and coherence by including calculations of Maximum Mutual Information (MMI) and entropy. We demonstrate the effectiveness of this system by using a set of custom evaluation metrics inspired by an abundance of previous research and based on tried-and-true principles of Natural Language Processing.

Thomas Conley, Jugal Kalita

Artificial Neural networks are mathematical models at their core. This truismpresents some fundamental difficulty when networks are tasked with Natural Language Processing. A key problem lies in measuring the similarity or distance among vectors in NLP embedding space, since the mathematical concept of distance does not always agree with the linguistic concept. We suggest that the best way to measure linguistic distance among vectors is by employing the Language Model (LM) that created them. We introduce Language Model Distance (LMD) for measuring accuracy of vector transformations based on the Distributional Hypothesis ( LMD Accuracy ). We show the efficacy of this metric by applying it to a simple neural network learning the Procrustes algorithm for bilingual word mapping.

Kaden Griffith, Jugal Kalita

This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations. We compare results produced by many neural configurations and find that most configurations outperform previously reported approaches on three of four datasets with significant increases in accuracy of over 20 percentage points. The best neural approaches boost accuracy by 30% when compared to the previous state-of-the-art on some datasets.

Ahmed Bensaoud, Nawaf Abudawaood, Jugal Kalita

Due to increasing threats from malicious software (malware) in both number and complexity, researchers have developed approaches to automatic detection and classification of malware, instead of analyzing methods for malware files manually in a time-consuming effort. At the same time, malware authors have developed techniques to evade signature-based detection techniques used by antivirus companies. Most recently, deep learning is being used in malware classification to solve this issue. In this paper, we use several convolutional neural network (CNN) models for static malware classification. In particular, we use six deep learning models, three of which are past winners of the ImageNet Large-Scale Visual Recognition Challenge. The other three models are CNN-SVM, GRU-SVM and MLP-SVM, which enhance neural models with support vector machines (SVM). We perform experiments using the Malimg dataset, which has malware images that were converted from Portable Executable malware binaries. The dataset is divided into 25 malware families. Comparisons show that the Inception V3 model achieves a test accuracy of 99.24%, which is better than the accuracy of 98.52% achieved by the current state-of-the-art system called the M-CNN model.