Farig Sadeque
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Farig Sadeque has a total of 131 co-authors. Here are the top co-authors by number of shared publications:
- Steven Bethard
University of Arizona
6 shared publications - Farhadul Islam
Department of CSE, BRAC University, Dhaka, Bangladesh
3 shared publications - Jannatun Noor
C2SG Research Group, Computer Science and Engineering, United International University, Dhaka, Bangladesh
3 shared publications - Joyanta Jyoti Mondal
Department of Computer and Information Sciences University of Delaware United States
3 shared publications - Meem Arafat Manab
Universidad Politécnica de Madrid
3 shared publications Nicolas Rey-Villamizar
3 shared publications
Latest Publications
- Open Access
- 28 August 2026
- Published by Elsevier in SSRN Electronic Journal
BengaliMCQ: Structure-Aware Retrieval-Augmented Generation for MCQ Generation and Answer Prediction in a Low-Resource Language
Traditional retrieval-augmented generation (RAG) frameworks process documents without attending to their hierarchical structure, leading to poor performance, especially in low-resource languages such as Bengali. To address this, we propose a structure-aware RAG framework that models Bengali textbooks as hierarchical graphs and uses a contrastively trained graph neural network to retrieve a small set of relevant passages. These passages provide focused context for a large language model, enabling topic-specific multiple-choice question (MCQ) generation and in-domain answer prediction. Experimental results demonstrate that our framework outperforms strong dense retrieval baselines across retrieval metrics, produces more relevant MCQs, and achieves superior answer prediction accuracy.
- 28 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessBengaliMCQ: Structure-Aware Retrieval-Augmented Generation for MCQ Generation and Answer Prediction in a Low-Resource Language
Traditional retrieval-augmented generation (RAG) frameworks process documents without attending to their hierarchical structure, leading to poor performance, especially in low-resource languages such as Bengali. To address this, we propose a structure-aware RAG framework that models Bengali textbooks as hierarchical graphs and uses a contrastively trained graph neural network to retrieve a small set of relevant passages. These passages provide focused context for a large language model, enabling topic-specific multiple-choice question (MCQ) generation and in-domain answer prediction. Experimental results demonstrate that our framework outperforms strong dense retrieval baselines across retrieval metrics, produces more relevant MCQs, and achieves superior answer prediction accuracy.
- Open Access
- 3 June 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14 (1) , e82545
Clinical Note Generation From Doctor-Patient Conversations Using Parameter-Efficient Fine-Tuning Large Language Models: Comparative Study
Background: Clinical note documentation is a vital yet time-intensive task in health care. While advancements in natural language processing have transformed many domains, generating accurate summaries of doctor-patient conversations remains underexplored due to the limited availability of open-source datasets. Large language models (LLMs), with their training on vast datasets, present a promising solution to this challenge. Objective: Precision in clinical summarization is crucial, as it directly impacts patient care and safety. This study aimed to evaluate the effectiveness of parameter-efficient, fine-tuned, decoder-only LLMs for clinical note generation from doctor-patient conversations. We focus on assessing medical accuracy, robustness, and the feasibility of parameter-efficient fine-tuning (PEFT) approaches under practical resource constraints. Methods: We used the Medical Training Summarization Dialog dataset containing 1700 doctor-patient conversations paired with clinical notes. Several decoder-only LLMs, including Mistral, Meditron, and Llama, were fine-tuned using PEFT techniques to reduce computational and memory overhead. Evaluation was performed using standard automatic metrics, including the Recall-Oriented Understudy for Gisting Evaluation score and bidirectional encoder representations from transformers score, to assess content overlap and semantic similarity between generated and reference clinical notes. In addition, an expert physician assessed the LLM-generated notes for medical accuracy, completeness, concision, relevance, and clinical coherence and readability. Results: Model performance was evaluated using the Recall-Oriented Understudy for Gisting Evaluation score and bidirectional encoder representations from transformers scores, demonstrating that Meditron-7B and Llama3-8B achieved state-of-the-art results among open-source, parameter-efficient, fine-tuned models, with Mistral-7B also performing competitively. The findings indicate that decoder-only LLMs, particularly Llama variants, outperform traditional models. Moreover, fine-tuning with higher quantization has the potential to further enhance performance. Human expert evaluation further indicated that Llama3-8B and Mistral-7B produced clinically coherent and accurate summaries, with Meditron-7B and Llama3-3B also performing reliably across evaluation criteria. The findings suggest that higher quantization during fine-tuning may improve efficiency without substantially compromising performance. Conclusions: This study underscores the potential of the PEFT of decoder-only LLMs to transform clinical workflows by streamlining medical documentation, thereby enabling health care professionals to dedicate more time to patient care. These models offer a scalable and resource-efficient alternative to traditional architectures and have the potential to streamline clinical documentation workflows.
- 3 June 2026
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 14 (1) , e82545
Open AccessClinical Note Generation From Doctor-Patient Conversations Using Parameter-Efficient Fine-Tuning Large Language Models: Comparative Study
Background: Clinical note documentation is a vital yet time-intensive task in health care. While advancements in natural language processing have transformed many domains, generating accurate summaries of doctor-patient conversations remains underexplored due to the limited availability of open-source datasets. Large language models (LLMs), with their training on vast datasets, present a promising solution to this challenge. Objective: Precision in clinical summarization is crucial, as it directly impacts patient care and safety. This study aimed to evaluate the effectiveness of parameter-efficient, fine-tuned, decoder-only LLMs for clinical note generation from doctor-patient conversations. We focus on assessing medical accuracy, robustness, and the feasibility of parameter-efficient fine-tuning (PEFT) approaches under practical resource constraints. Methods: We used the Medical Training Summarization Dialog dataset containing 1700 doctor-patient conversations paired with clinical notes. Several decoder-only LLMs, including Mistral, Meditron, and Llama, were fine-tuned using PEFT techniques to reduce computational and memory overhead. Evaluation was performed using standard automatic metrics, including the Recall-Oriented Understudy for Gisting Evaluation score and bidirectional encoder representations from transformers score, to assess content overlap and semantic similarity between generated and reference clinical notes. In addition, an expert physician assessed the LLM-generated notes for medical accuracy, completeness, concision, relevance, and clinical coherence and readability. Results: Model performance was evaluated using the Recall-Oriented Understudy for Gisting Evaluation score and bidirectional encoder representations from transformers scores, demonstrating that Meditron-7B and Llama3-8B achieved state-of-the-art results among open-source, parameter-efficient, fine-tuned models, with Mistral-7B also performing competitively. The findings indicate that decoder-only LLMs, particularly Llama variants, outperform traditional models. Moreover, fine-tuning with higher quantization has the potential to further enhance performance. Human expert evaluation further indicated that Llama3-8B and Mistral-7B produced clinically coherent and accurate summaries, with Meditron-7B and Llama3-3B also performing reliably across evaluation criteria. The findings suggest that higher quantization during fine-tuning may improve efficiency without substantially compromising performance. Conclusions: This study underscores the potential of the PEFT of decoder-only LLMs to transform clinical workflows by streamlining medical documentation, thereby enabling health care professionals to dedicate more time to patient care. These models offer a scalable and resource-efficient alternative to traditional architectures and have the potential to streamline clinical documentation workflows.
- Open Access
A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs
Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The first, a Transcript-Based Pipeline, uses large dialect sentence contexts from audio transcripts. The second, a more effective Standardized Sentence-Pairs Pipeline, utilizes structured local\_dialect:standard\_bengali sentence pairs. We evaluated both pipelines across six Bengali dialects and multiple LLMs using BLEU, ChrF, WER, and BERTScore. Our findings show that the sentence-pair pipeline consistently outperforms the transcript-based one, reducing Word Error Rate (WER) from 76\% to 55\% for the Chittagong dialect. Critically, this RAG approach enables smaller models (e.g., Llama-3.1-8B) to outperform much larger models (e.g., GPT-OSS-120B), demonstrating that a well-designed retrieval strategy can be more crucial than model size. This work contributes an effective, fine-tuning-free solution for low-resource dialect translation, offering a practical blueprint for preserving linguistic diversity.
Open AccessA Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs
Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The first, a Transcript-Based Pipeline, uses large dialect sentence contexts from audio transcripts. The second, a more effective Standardized Sentence-Pairs Pipeline, utilizes structured local\_dialect:standard\_bengali sentence pairs. We evaluated both pipelines across six Bengali dialects and multiple LLMs using BLEU, ChrF, WER, and BERTScore. Our findings show that the sentence-pair pipeline consistently outperforms the transcript-based one, reducing Word Error Rate (WER) from 76\% to 55\% for the Chittagong dialect. Critically, this RAG approach enables smaller models (e.g., Llama-3.1-8B) to outperform much larger models (e.g., GPT-OSS-120B), demonstrating that a well-designed retrieval strategy can be more crucial than model size. This work contributes an effective, fine-tuning-free solution for low-resource dialect translation, offering a practical blueprint for preserving linguistic diversity.
- Open Access
Advancing Bangla Machine Translation Through Informal Datasets
Bangla is the sixth most widely spoken language globally, with approximately 234 million native speakers. However, progress in open-source Bangla machine translation remains limited. Most online resources are in English and often remain untranslated into Bangla, excluding millions from accessing essential information. Existing research in Bangla translation primarily focuses on formal language, neglecting the more commonly used informal language. This is largely due to the lack of pairwise Bangla-English data and advanced translation models. If datasets and models can be enhanced to better handle natural, informal Bangla, millions of people will benefit from improved online information access. In this research, we explore current state-of-the-art models and propose improvements to Bangla translation by developing a dataset from informal sources like social media and conversational texts. This work aims to advance Bangla machine translation by focusing on informal language translation and improving accessibility for Bangla speakers in the digital world.
Open AccessAdvancing Bangla Machine Translation Through Informal Datasets
Bangla is the sixth most widely spoken language globally, with approximately 234 million native speakers. However, progress in open-source Bangla machine translation remains limited. Most online resources are in English and often remain untranslated into Bangla, excluding millions from accessing essential information. Existing research in Bangla translation primarily focuses on formal language, neglecting the more commonly used informal language. This is largely due to the lack of pairwise Bangla-English data and advanced translation models. If datasets and models can be enhanced to better handle natural, informal Bangla, millions of people will benefit from improved online information access. In this research, we explore current state-of-the-art models and propose improvements to Bangla translation by developing a dataset from informal sources like social media and conversational texts. This work aims to advance Bangla machine translation by focusing on informal language translation and improving accessibility for Bangla speakers in the digital world.
- Open Access
Is Lying Only Sinful in Islam? Exploring Religious Bias in Multilingual Large Language Models Across Major Religions
While recent developments in large language models have improved bias detection and classification, sensitive subjects like religion still present challenges because even minor errors can result in severe misunderstandings. In particular, multilingual models often misrepresent religions and have difficulties being accurate in religious contexts. To address this, we introduce BRAND: Bilingual Religious Accountable Norm Dataset, which focuses on the four main religions of South Asia: Buddhism, Christianity, Hinduism, and Islam, containing over 2,400 entries, and we used three different types of prompts in both English and Bengali. Our results indicate that models perform better in English than in Bengali and consistently display bias toward Islam, even when answering religion-neutral questions. These findings highlight persistent bias in multilingual models when similar questions are asked in different languages. We further connect our findings to the broader issues in HCI regarding religion and spirituality.
Open AccessIs Lying Only Sinful in Islam? Exploring Religious Bias in Multilingual Large Language Models Across Major Religions
While recent developments in large language models have improved bias detection and classification, sensitive subjects like religion still present challenges because even minor errors can result in severe misunderstandings. In particular, multilingual models often misrepresent religions and have difficulties being accurate in religious contexts. To address this, we introduce BRAND: Bilingual Religious Accountable Norm Dataset, which focuses on the four main religions of South Asia: Buddhism, Christianity, Hinduism, and Islam, containing over 2,400 entries, and we used three different types of prompts in both English and Bengali. Our results indicate that models perform better in English than in Bengali and consistently display bias toward Islam, even when answering religion-neutral questions. These findings highlight persistent bias in multilingual models when similar questions are asked in different languages. We further connect our findings to the broader issues in HCI regarding religion and spirituality.
- Open Access
Bridging Human and Model Perspectives: A Comparative Analysis of Political Bias Detection in News Media Using Large Language Models
Detecting political bias in news media is a complex task that requires interpreting subtle linguistic and contextual cues. Although recent advances in Natural Language Processing (NLP) have enabled automatic bias classification, the extent to which large language models (LLMs) align with human judgment still remains relatively underexplored and not yet well understood. This study aims to present a comparative framework for evaluating the detection of political bias across human annotations and multiple LLMs, including GPT, BERT, RoBERTa, and FLAN. We construct a manually annotated dataset of news articles and assess annotation consistency, bias polarity, and inter-model agreement to quantify divergence between human and model perceptions of bias. Experimental results show that among traditional transformer-based models, RoBERTa achieves the highest alignment with human labels, whereas generative models such as GPT demonstrate the strongest overall agreement with human annotations in a zero-shot setting. Among all transformer-based baselines, our fine-tuned RoBERTa model acquired the highest accuracy and the strongest alignment with human-annotated labels. Our findings highlight systematic differences in how humans and LLMs perceive political slant, underscoring the need for hybrid evaluation frameworks that combine human interpretability with model scalability in automated media bias detection.
Open AccessBridging Human and Model Perspectives: A Comparative Analysis of Political Bias Detection in News Media Using Large Language Models
Detecting political bias in news media is a complex task that requires interpreting subtle linguistic and contextual cues. Although recent advances in Natural Language Processing (NLP) have enabled automatic bias classification, the extent to which large language models (LLMs) align with human judgment still remains relatively underexplored and not yet well understood. This study aims to present a comparative framework for evaluating the detection of political bias across human annotations and multiple LLMs, including GPT, BERT, RoBERTa, and FLAN. We construct a manually annotated dataset of news articles and assess annotation consistency, bias polarity, and inter-model agreement to quantify divergence between human and model perceptions of bias. Experimental results show that among traditional transformer-based models, RoBERTa achieves the highest alignment with human labels, whereas generative models such as GPT demonstrate the strongest overall agreement with human annotations in a zero-shot setting. Among all transformer-based baselines, our fine-tuned RoBERTa model acquired the highest accuracy and the strongest alignment with human-annotated labels. Our findings highlight systematic differences in how humans and LLMs perceive political slant, underscoring the need for hybrid evaluation frameworks that combine human interpretability with model scalability in automated media bias detection.
- Open Access
destroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity
Advancements in Machine Learning & Neural Networks in recent years have led to widespread implementations of Natural Language Processing across a variety of fields with remarkable success, solving a wide range of complicated problems. However, recent research has shown that machine learning models may be vulnerable in a number of ways, putting both the models and the systems theyre used in at risk. In this paper, we intend to analyze and experiment with the best of existing adversarial attack recipes and create new ones. We concentrated on developing a novel adversarial attack strategy on current state-of-the-art machine learning models by producing ambiguous inputs for the models to confound them and then constructing the path to the future development of the robustness of the models. We will develop adversarial instances with maximum perplexity, utilizing machine learning and deep learning approaches in order to trick the models. In our attack recipe, we will analyze several datasets and focus on creating obfuscous adversary examples to put the models in a state of perplexity, and by including the Bangla Language in the field of adversarial attacks. We strictly uphold utility usage reduction and efficiency throughout our work.
Open AccessdestroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity
Advancements in Machine Learning & Neural Networks in recent years have led to widespread implementations of Natural Language Processing across a variety of fields with remarkable success, solving a wide range of complicated problems. However, recent research has shown that machine learning models may be vulnerable in a number of ways, putting both the models and the systems theyre used in at risk. In this paper, we intend to analyze and experiment with the best of existing adversarial attack recipes and create new ones. We concentrated on developing a novel adversarial attack strategy on current state-of-the-art machine learning models by producing ambiguous inputs for the models to confound them and then constructing the path to the future development of the robustness of the models. We will develop adversarial instances with maximum perplexity, utilizing machine learning and deep learning approaches in order to trick the models. In our attack recipe, we will analyze several datasets and focus on creating obfuscous adversary examples to put the models in a state of perplexity, and by including the Bangla Language in the field of adversarial attacks. We strictly uphold utility usage reduction and efficiency throughout our work.
- Open Access
BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference
Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited. Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous sentence pairs, and inadequate linguistic diversity, which hinder effective model training and evaluation. To address these limitations, we introduce BNLI, a refined and linguistically curated Bengali NLI dataset designed to support robust language understanding and inference modeling. The dataset was constructed through a rigorous annotation pipeline emphasizing semantic clarity and balance across entailment, contradiction, and neutrality classes. We benchmarked BNLI using a suite of state-of-the-art transformer-based architectures, including multilingual and Bengali-specific models, to assess their ability to capture complex semantic relations in Bengali text. The experimental findings highlight the improved reliability and interpretability achieved with BNLI, establishing it as a strong foundation for advancing research in Bengali and other low-resource language inference tasks.
Open AccessBNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference
Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited. Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous sentence pairs, and inadequate linguistic diversity, which hinder effective model training and evaluation. To address these limitations, we introduce BNLI, a refined and linguistically curated Bengali NLI dataset designed to support robust language understanding and inference modeling. The dataset was constructed through a rigorous annotation pipeline emphasizing semantic clarity and balance across entailment, contradiction, and neutrality classes. We benchmarked BNLI using a suite of state-of-the-art transformer-based architectures, including multilingual and Bengali-specific models, to assess their ability to capture complex semantic relations in Bengali text. The experimental findings highlight the improved reliability and interpretability achieved with BNLI, establishing it as a strong foundation for advancing research in Bengali and other low-resource language inference tasks.
- Open Access
Transforming Mentorship: An AI Powered Chatbot Approach to University Guidance
University students face immense challenges during their undergraduate lives, often being deprived of personalized on-demand guidance that mentors fail to provide at scale. Digital tools exist, but there is a serious lack of customized coaching for newcomers. This paper presents an AI-powered chatbot that will serve as a mentor for the students of BRAC University. The main component is a data ingestion pipeline that efficiently processes and updates information from diverse sources, such as CSV files and university webpages. The chatbot retrieves information through a hybrid approach, combining BM25 lexical ranking with ChromaDB semantic retrieval, and uses a Large Language Model, LLaMA-3.3-70B, to generate conversational responses. The generated text was found to be semantically highly relevant, with a BERTScore of 0.831 and a METEOR score of 0.809. The data pipeline was also very efficient, taking 106.82 seconds for updates, compared to 368.62 seconds for new data. This chatbot will be able to help students by responding to their queries, helping them to get a better understanding of university life, and assisting them to plan better routines for their semester in the open-credit university.
Open AccessTransforming Mentorship: An AI Powered Chatbot Approach to University Guidance
University students face immense challenges during their undergraduate lives, often being deprived of personalized on-demand guidance that mentors fail to provide at scale. Digital tools exist, but there is a serious lack of customized coaching for newcomers. This paper presents an AI-powered chatbot that will serve as a mentor for the students of BRAC University. The main component is a data ingestion pipeline that efficiently processes and updates information from diverse sources, such as CSV files and university webpages. The chatbot retrieves information through a hybrid approach, combining BM25 lexical ranking with ChromaDB semantic retrieval, and uses a Large Language Model, LLaMA-3.3-70B, to generate conversational responses. The generated text was found to be semantically highly relevant, with a BERTScore of 0.831 and a METEOR score of 0.809. The data pipeline was also very efficient, taking 106.82 seconds for updates, compared to 368.62 seconds for new data. This chatbot will be able to help students by responding to their queries, helping them to get a better understanding of university life, and assisting them to plan better routines for their semester in the open-credit university.
- Open Access
Exploring and Mitigating Gender Bias in Encoder-Based Transformer Models
Gender bias in language models has gained increasing attention in the field of natural language processing. Encoder-based transformer models, which have achieved state-of-the-art performance in various language tasks, have been shown to exhibit strong gender biases inherited from their training data. This paper investigates gender bias in contextualized word embeddings, a crucial component of transformer-based models. We focus on prominent architectures such as BERT, ALBERT, RoBERTa, and DistilBERT to examine their vulnerability to gender bias. To quantify the degree of bias, we introduce a novel metric, MALoR, which assesses bias based on model probabilities for filling masked tokens. We further propose a mitigation approach involving continued pre-training on a gender-balanced dataset generated via Counterfactual Data Augmentation. Our experiments reveal significant reductions in gender bias scores across different pronoun pairs. For instance, in BERT-base, bias scores for "he-she" dropped from 1.27 to 0.08, and "his-her" from 2.51 to 0.36 following our mitigation approach. We also observed similar improvements across other models, with "male-female" bias decreasing from 1.82 to 0.10 in BERT-large. Our approach effectively reduces gender bias without compromising model performance on downstream tasks.
Open AccessExploring and Mitigating Gender Bias in Encoder-Based Transformer Models
Gender bias in language models has gained increasing attention in the field of natural language processing. Encoder-based transformer models, which have achieved state-of-the-art performance in various language tasks, have been shown to exhibit strong gender biases inherited from their training data. This paper investigates gender bias in contextualized word embeddings, a crucial component of transformer-based models. We focus on prominent architectures such as BERT, ALBERT, RoBERTa, and DistilBERT to examine their vulnerability to gender bias. To quantify the degree of bias, we introduce a novel metric, MALoR, which assesses bias based on model probabilities for filling masked tokens. We further propose a mitigation approach involving continued pre-training on a gender-balanced dataset generated via Counterfactual Data Augmentation. Our experiments reveal significant reductions in gender bias scores across different pronoun pairs. For instance, in BERT-base, bias scores for "he-she" dropped from 1.27 to 0.08, and "his-her" from 2.51 to 0.36 following our mitigation approach. We also observed similar improvements across other models, with "male-female" bias decreasing from 1.82 to 0.10 in BERT-large. Our approach effectively reduces gender bias without compromising model performance on downstream tasks.