Souvika Sarkar

Shahana Akter, Yatharth Vohra, Ankita Shukla et al.

Multi-label topic classification without labeled training data is a challenging task, specially when documents contain complex relational information. We present a zero-shot multi-label topic classification framework and systematically investigate how per-article knowledge graph augmentation affects its performance. The base framework classifies topics in documents without labeled training data and has four variants: article-only classification, keyword-enhanced classification, and self-consistency decoding variants of both. Then, we augment each base variant with per article knowledge graph. This graph is extracted from the input document through a pipeline similar to KGGen based on subject-predicate-object triples. We test all eight methods, four base and four graph augmented on fifteen LLMs and eight multi-label datasets across different domains. For the base framework, keyword-enhanced classification (AK) is the best performing method, and six out of fifteen LLMs surpass the sentence-encoder baseline. Graph augmentation has positive and negative impacts on small and large models, respectively. This shows that larger models already contain enough relational information from pretraining. Furthermore, the self-consistency decoding variant does not show performance improvements in any experiment while increasing computation costs about fivefold.

Souvika Sarkar, Mohammad Fakhruddin Babar, Md Mahadi Hassan et al.

This paper presents a performance study of transformer language models under different hardware configurations and accuracy requirements and derives empirical observations about these resource/accuracy trade-offs. In particular, we study how the most commonly used BERT-based language models (viz., BERT, RoBERTa, DistilBERT, and TinyBERT) perform on embedded systems. We tested them on four off-the-shelf embedded platforms (Raspberry Pi, Jetson, UP2, and UDOO) with 2 GB and 4 GB memory (i.e., a total of eight hardware configurations) and four datasets (i.e., HuRIC, GoEmotion, CoNLL, WNUT17) running various NLP tasks. Our study finds that executing complex NLP tasks (such as "sentiment" classification) on embedded systems is feasible even without any GPUs (e.g., Raspberry Pi with 2 GB of RAM). Our findings can help designers understand the deployability and performance of transformer language models, especially those based on BERT architectures.

Souvika Sarkar, Dongji Feng, Shubhra Kanti Karmaker Santu

Sentence encoders have indeed been shown to achieve superior performances for many downstream text-mining tasks and, thus, claimed to be fairly general. Inspired by this, we performed a detailed study on how to leverage these sentence encoders for the "zero-shot topic inference" task, where the topics are defined/provided by the users in real-time. Extensive experiments on seven different datasets demonstrate that Sentence-BERT demonstrates superior generality compared to other encoders, while Universal Sentence Encoder can be preferred when efficiency is a top priority.

Mousumi Akter, Souvika Sarkar, Shubhra Kanti Karmaker Santu

This paper presents a high-quality dataset for evaluating the quality of Bangla word embeddings, which is a fundamental task in the field of Natural Language Processing (NLP). Despite being the 7th most-spoken language in the world, Bangla is a low-resource language and popular NLP models fail to perform well. Developing a reliable evaluation test set for Bangla word embeddings are crucial for benchmarking and guiding future research. We provide a Mikolov-style word analogy evaluation set specifically for Bangla, with a sample size of 16678, as well as a translated and curated version of the Mikolov dataset, which contains 10594 samples for cross-lingual research. Our experiments with different state-of-the-art embedding models reveal that Bangla has its own unique characteristics, and current embeddings for Bangla still struggle to achieve high accuracy on both datasets. We suggest that future research should focus on training models with larger datasets and considering the unique morphological characteristics of Bangla. This study represents the first step towards building a reliable NLP system for the Bangla language1.

R. Alexander Knipper, Indrani Dey, Souvika Sarkar et al.

Virtual Labs offer valuable opportunities for hands-on, inquiry-based science learning, yet teachers often struggle to adapt them to fit their instructional goals. Third-party materials may not align with classroom needs, and developing custom resources can be time-consuming and difficult to scale. Recent advances in Large Language Models (LLMs) offer a promising avenue for addressing these limitations. In this paper, we introduce a novel alignment framework for instructional goal-aligned question generation, enabling teachers to leverage LLMs to produce simulation-aligned, pedagogically meaningful questions through natural language interaction. The framework integrates four components: instructional goal understanding via teacher-LLM dialogue, lab understanding via knowledge unit and relationship analysis, a question taxonomy for structuring cognitive and pedagogical intent, and the TELeR taxonomy for controlling prompt detail. Early design choices were informed by a small teacher-assisted case study, while our final evaluation analyzed over 1,100 questions from 19 open-source LLMs. With goal and lab understanding grounding questions in teacher intent and simulation context, the question taxonomy elevates cognitive demand (open-ended formats and relational types raise quality by 0.29-0.39 points), and optimized TELeR prompts enhance format adherence (80% parsability, >90% adherence). Larger models yield the strongest gains: parsability +37.1%, adherence +25.7%, and average quality +0.8 Likert points.

Eftekhar Hossain, Sanjeev Kumar Sinha, Naman Bansal et al.

One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves assimilating diverse opinions from multiple expert peers, formulating one's self-judgment as a senior expert, and then summarizing all these perspectives into a concise holistic overview to make an overall recommendation. This process is time-consuming and can be compromised by human factors like fatigue, inconsistency, missing tiny details, etc. Given the latest major developments in Large Language Models (LLMs), it is very compelling to rigorously study whether LLMs can help metareviewers perform this important task better. In this paper, we perform a case study with three popular LLMs, i.e., GPT-3.5, LLaMA2, and PaLM2, to assist meta-reviewers in better comprehending multiple experts perspectives by generating a controlled multi-perspective summary (MPS) of their opinions. To achieve this, we prompt three LLMs with different types/levels of prompts based on the recently proposed TELeR taxonomy. Finally, we perform a detailed qualitative study of the MPSs generated by the LLMs and report our findings.

Md. Najib Hasan, Touseef Hasan, Souvika Sarkar

Large Language Models (LLMs) are increasingly used as automated annotators to scale dataset creation, yet their reliability as unbiased annotators--especially for low-resource and identity-sensitive settings--remains poorly understood. In this work, we study the behavior of LLMs as zero-shot annotators for Bangla hate speech, a task where even human agreement is challenging, and annotator bias can have serious downstream consequences. We conduct a systematic benchmark of 17 LLMs using a unified evaluation framework. Our analysis uncovers annotator bias and substantial instability in model judgments. Surprisingly, increased model scale does not guarantee improved annotation quality--smaller, more task-aligned models frequently exhibit more consistent behavior than their larger counterparts. These results highlight important limitations of current LLMs for sensitive annotation tasks in low-resource languages and underscore the need for careful evaluation before deployment.

Touseef Hasan, Laila Cure, Souvika Sarkar

Public service information systems are often fragmented, inconsistently formatted, and outdated. These characteristics create low-resource retrieval environments that hinder timely access to critical services. We investigate retrieval challenges in such settings through the domain of food pantry access, a socially urgent problem given persistent food insecurity. We develop an AI-powered conversational retrieval system that scrapes and indexes publicly available pantry data and employs a Retrieval-Augmented Generation (RAG) pipeline to support natural language queries via a web interface. We conduct a pilot evaluation study using community-sourced queries to examine system behavior in realistic scenarios. Our analysis reveals key limitations in retrieval robustness, handling underspecified queries, and grounding over inconsistent knowledge bases. This ongoing work exposes fundamental IR challenges in low-resource environments and motivates future research on robust conversational retrieval to improve access to critical public resources.

Md. Najib Hasan, Mohammad Fakhruddin Babar, Souvika Sarkar et al.

Open Large Language Model (LLM) benchmarks, such as HELM and BIG-bench, offer standardized, transparent protocols that facilitate the fair comparison, reproducibility, and iterative advancement of Language Models (LMs). However, their openness also introduces critical and underexplored pitfalls. This study exposes these weaknesses by systematically constructing ``cheating'' models -- smaller variants of BART, T5, and GPT-2 fine-tuned directly on public test sets -- which achieve top rankings on a prominent open, holistic benchmark (HELM) despite poor generalization and limited practical utility. Our findings underscore three key insights: \ca high leaderboard performance on open benchmarks may not always reflect real-world effectiveness; \cb private or dynamic benchmarks must complement open evaluations to safeguard integrity; and \cc a fundamental reevaluation of current benchmarking practices is essential to ensure robust and trustworthy LM assessments.

John Salvador, Naman Bansal, Mousumi Akter et al.

Semantic Overlap Summarization (SOS) is a constrained multi-document summarization task, where the constraint is to capture the common/overlapping information between two alternative narratives. In this work, we perform a benchmarking study of popular Large Language Models (LLMs) exclusively on the SOS task. Additionally, we introduce the PrivacyPolicyPairs (3P) dataset to expand the space of SOS benchmarks in terms of quantity and variety. This dataset provides 135 high-quality SOS data samples sourced from privacy policy documents. We then use a standard prompting taxonomy called TELeR to create and evaluate 905,216 distinct LLM-generated summaries over two SOS datasets from different domains, and we further conduct human evaluation on a subset of 540 samples. We conclude the paper by analyzing models' performances and the reliability of automatic evaluation. The code and datasets used to conduct this study are available at https://anonymous.4open.science/r/llm_eval-E16D.

Souvika Sarkar, Mohammad Fakhruddin Babar, Monowar Hasan et al.

Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended training durations, and scalability issues. To address these issues, we introduce a concept of hierarchical, distributed LLM architecture that aims at enhancing the accessibility and deployability of LLMs across heterogeneous computing platforms, including general-purpose computers (e.g., laptops) and IoT-style devices (e.g., embedded systems). By introducing a "layered" approach, the proposed architecture enables on-demand accessibility to LLMs as a customizable service. This approach also ensures optimal trade-offs between the available computational resources and the user's application needs. We envision that the concept of hierarchical LLM will empower extensive, crowd-sourced user bases to harness the capabilities of LLMs, thereby fostering advancements in AI technology in general.

Amit Das, Md. Najib Hasan, Souvika Sarkar et al.

Large Language Models (LLMs) have demonstrated remarkable proficiency in generating text that closely resemble human writing. However, they often generate factually incorrect statements, a problem typically referred to as 'hallucination'. Addressing hallucination is crucial for enhancing the reliability and effectiveness of LLMs. While much research has focused on hallucinations in English, our study extends this investigation to conversational data in three languages: Hindi, Farsi, and Mandarin. We offer a comprehensive analysis of a dataset to examine both factual and linguistic errors in these languages for GPT-3.5, GPT-4o, Llama-3.1, Gemma-2.0, DeepSeek-R1 and Qwen-3. We found that LLMs produce very few hallucinated responses in Mandarin but generate a significantly higher number of hallucinations in Hindi and Farsi.

Souvika Sarkar, Md. Najib Hasan, Santu Karmaker

Bangla, a language spoken by over 300 million native speakers and ranked as the sixth most spoken language worldwide, presents unique challenges in natural language processing (NLP) due to its complex morphological characteristics and limited resources. While recent Large Decoder Based models (LLMs), such as GPT, LLaMA, and DeepSeek, have demonstrated excellent performance across many NLP tasks, their effectiveness in Bangla remains largely unexplored. In this paper, we establish the first benchmark comparing decoder-based LLMs with classic encoder-based models for Zero-Shot Multi-Label Classification (Zero-Shot-MLC) task in Bangla. Our evaluation of 32 state-of-the-art models reveals that, existing so-called powerful encoders and decoders still struggle to achieve high accuracy on the Bangla Zero-Shot-MLC task, suggesting a need for more research and resources for Bangla NLP.

Amit Das, Zheng Zhang, Najib Hasan et al.

Data annotation, the practice of assigning descriptive labels to raw data, is pivotal in optimizing the performance of machine learning models. However, it is a resource-intensive process susceptible to biases introduced by annotators. The emergence of sophisticated Large Language Models (LLMs) presents a unique opportunity to modernize and streamline this complex procedure. While existing research extensively evaluates the efficacy of LLMs, as annotators, this paper delves into the biases present in LLMs when annotating hate speech data. Our research contributes to understanding biases in four key categories: gender, race, religion, and disability with four LLMs: GPT-3.5, GPT-4o, Llama-3.1 and Gemma-2. Specifically targeting highly vulnerable groups within these categories, we analyze annotator biases. Furthermore, we conduct a comprehensive examination of potential factors contributing to these biases by scrutinizing the annotated data. We introduce our custom hate speech detection dataset, HateBiasNet, to conduct this research. Additionally, we perform the same experiments on the ETHOS (Mollas et al. 2022) dataset also for comparative analysis. This paper serves as a crucial resource, guiding researchers and practitioners in harnessing the potential of LLMs for data annotation, thereby fostering advancements in this critical field.