Papers by Md Rizwan Parvez
MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing frameworks for large language models are tailored to domains such as mathematics, coding, or web automation. |
| Approach: | They propose a hierarchical multi-agent plug-and-play framework with customized toolsets and agentic scaffolds for map-integrated geospatial reasoning. |
| Outcome: | The proposed framework decouples planning from execution and reduces cognitive load on users. |
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing labeled datasets are heavily imbalanced, limiting the QA performance in this domain. |
| Approach: | They propose a question answering task that captures relevant text segments from unlabeled policy documents and expands the positive examples in the training set. |
| Outcome: | The proposed framework elevates the baseline by a large margin (10% F1) and achieves a new state-of-the-art F1 score of 50%. |
A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations (2024.emnlp-main)
Copied to clipboard
Md Tahmid Rahman Laskar, Sawsan Alqahtani, M Saiful Bari, Mizanur Rahman, Mohammad Abdullah Matin Khan, Haidar Khan, Israt Jahan, Amran Bhuiyan, Chee Wei Tan, Md Rizwan Parvez, Enamul Hoque, Shafiq Joty, Jimmy Huang
| Challenge: | Large Language Models (LLMs) have gained significant attention due to their capabilities in performing diverse tasks across domains. |
| Approach: | They review the primary challenges and limitations causing inconsistencies in evaluations . early models could generate coherent text but limited to simple tasks . |
| Outcome: | The proposed evaluations are reproducible, reliable, and robust. |
TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for identifying adversarial techniques in security texts face a trade-off: generic models with limited domain precision or resource-intensive pipelines. |
| Approach: | They propose a domain-specific retrieval-augmented generation framework that integrates off-the-shelf retrievers, instruction-tuned LLMs, and minimal text–technique pairs. |
| Outcome: | The proposed framework improves retrieval quality and domain specificity without extensive optimizations. |
CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing algorithms and machine learning methods require model training, parameter tuning, and retraining when accommodating data updates. |
| Approach: | They propose a multi-agent framework that leverages the reasoning capabilities of Large Language Models into the geo-spatial domain to solve the popular path query. |
| Outcome: | Experiments on real and synthetic datasets show that CompassLLM performs better than existing models while being cost-effective. |
MapCoder: Multi-Agent Code Generation for Competitive Problem Solving (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive proficiency in natural language processing, but performance in code generation tasks remains limited. |
| Approach: | They propose a framework that emulates the full cycle of program synthesis as observed in humans. |
| Outcome: | The proposed framework replicates the full cycle of program synthesis as observed in human developers. |
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Data-driven storytelling uses visual aids and visualizations to convey insights. |
| Approach: | They propose a task for data story generation using large language models and a benchmark containing 1,449 stories from diverse sources. |
| Outcome: | The proposed framework outperforms non-agentic counterparts in both model-based and human evaluations, but also reveals unique challenges in data story generation. |
Mina: A Multilingual LLM-Powered Legal Assistant Agent for Empowering Access to Justice in Bangladesh (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing AI legal assistants lack Bengali-language support and jurisdiction-specific adaptation, limiting their effectiveness. |
| Approach: | They developed a multilingual LLM-based legal assistant tailored for the Bangladeshi context that employs multilingual embeddings and a RAG-based chain-of-tools framework for retrieval, reasoning, translation, and document generation. |
| Outcome: | Evaluated by law faculty from leading Bangladeshi universities across all stages of the 2022 and 2023 Bangladesh Bar Council examinations, Mina achieved scores of 75–80% in preliminary MCQs, written, and simulated viva voce components. |
Open-RAG: Enhanced Retrieval Augmented Reasoning with Open-Source Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to integrate Large Language Models with external knowledge suffer from limited reasoning capabilities, especially when using open-source LLMs. |
| Approach: | They propose a framework that transforms an arbitrary dense LLM into a parameter-efficient sparse mixture of experts (MoE) model capable of handling complex reasoning tasks. |
| Outcome: | The proposed framework transforms an arbitrary dense LLM into a parameter-efficient sparse mixture of experts (MoE) model capable of handling complex reasoning tasks, including both single- and multi-hop queries. |
DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards (2026.findings-eacl)
Copied to clipboard
Aaryaman Kartha, Ahmed Masry, Mohammed Saidul Islam, Thinh Lang, Shadikur Rahman, Ridwan Mahbub, Mizanur Rahman, Mahir Ahmed, Md Rizwan Parvez, Enamul Hoque, Shafiq Joty
| Challenge: | Existing question-answering benchmarks for data visualizations focus on static charts instead of interactive dashboards. |
| Approach: | They propose a benchmark to assess how vision-language GUI agents comprehend and interact with real-world dashboards. |
| Outcome: | The first benchmark explicitly designed to assess how vision-language GUI agents comprehend and interact with real-world dashboards. |
XCodeEval: An Execution-based Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments. |
| Approach: | They propose to use a multilingual multitask benchmark to evaluate large language models that can generate codes from natural language descriptions, repair buggy codes, and translate between languages. |
| Outcome: | The proposed model performs 7 tasks covering up to 11 languages with execution-level parallelism and 25 M document-level coding examples (16.5 B tokens) |
Evaluating the Values of Sources in Transfer Learning (2021.naacl-main)
Copied to clipboard
| Challenge: | Transfer learning is a form of learning that adapts a model trained on data-rich sources to low-resource targets. |
| Approach: | They propose a source valuation framework that quantifies the usefulness of the sources in transfer learning by using the Shapley value method. |
| Outcome: | The proposed framework is effective in choosing useful transfer sources and the source values match the intuitive source-target similarity. |
MapQaTor: An Extensible Framework for Efficient Annotation of Map-Based QA Datasets (2025.acl-demo)
Copied to clipboard
| Challenge: | Mapping and navigation services struggle to handle natural language geospatial queries. |
| Approach: | They introduce an extensible open-source framework that streamlines the creation of reproducible, traceable map-based QA datasets. |
| Outcome: | a new open-source framework streamlines the creation of reproducible, traceable map-based QA datasets. |
Robust Text Classifier on Test-Time Budgets (D19-1)
Copied to clipboard
| Challenge: | Recent advances in deep neural networks (DNNs) achieve high accuracy on many text classification tasks. |
| Approach: | They propose a generic framework for learning a robust text classification model . they use a data aggregation method to train the classifier on a large corpus of text . |
| Outcome: | The proposed framework achieves consistent speedup with little degradation in accuracy on four benchmark text classification tasks. |
ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning (2024.findings-acl)
Copied to clipboard
| Challenge: | Charts provide visual representations of data and are used for analyzing information, addressing queries, and conveying insights to others. |
| Approach: | They propose a chart-specific vision-language Instruction-following dataset with 191K instructions and a pipeline model that extracts chart data tables and inputs them into a LLM. |
| Outcome: | The proposed model can solve a wide range of chart-related tasks, achieving state-of-the-art results on four tasks. |
Self-Consistency from Only Two Samples: CoT–PoT Ensembling for Efficient LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models but it comes at a high computational cost due to extensive sampling. |
| Approach: | They propose a hybrid ensembling approach that leverages the complementary strengths of Chain-of-Thought and Program-of -Thus . they propose encapsulating two different modes of reasoning to create a single output and a final answer is selected as the most frequently occurring one among these outputs. |
| Outcome: | The proposed approach reduces the number of samples required for SC by 9.3x . the majority of tasks can be addressed with only two samples, which has not been possible with prior methods. |
ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering (2025.findings-acl)
Copied to clipboard
Ahmed Masry, Mohammed Saidul Islam, Mahir Ahmed, Aayush Bajaj, Firoz Kabir, Aaryaman Kartha, Md Tahmid Rahman Laskar, Mizanur Rahman, Shadikur Rahman, Mehrad Shahmohammadi, Megh Thakkar, Md Rizwan Parvez, Enamul Hoque, Shafiq Joty
| Challenge: | Chart Question Answering systems are limited in their ability to interpret data visually and reason with visual representations. |
| Approach: | They propose a chart-based chart question-answering system that includes 1,341 charts from 99 diverse sources and 1,948 questions in various types. |
| Outcome: | The new benchmark includes 1,341 charts from 99 diverse sources and 1,948 questions in various types. |
CodeSim: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant strides in code generation and problem solving. |
| Approach: | They propose a multi-agent code generation framework that integrates human-like perception to address the stages of program synthesis. |
| Outcome: | The proposed framework achieves state-of-the-art (pass@1) results and shows potential for even greater enhancement when cascaded with external debuggers. |
Building Language Models for Text with Named Entities (P18-1)
Copied to clipboard
| Challenge: | Existing language models fail to predict the entity names due to their wide variations. |
| Approach: | They propose a language model which can learn the entity names by leveraging their entity type information. |
| Outcome: | The proposed model achieves 52.2% better perplexity in recipe generation and 22.06% on code generation than state-of-the-art language models. |
Retrieval Augmented Code Generation and Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Software developers often recall parts of source code or code summaries that they had written in the past while implementing software or documenting them. |
| Approach: | They propose a retrieval augmented framework that retrieves relevant code or summaries from a database and provides them as a supplement to code generation or summarization models. |
| Outcome: | The proposed framework can search for relevant code or summaries from retrieval databases and can work with unimodal (only code or natural language description) or bimodal instances (code-description pairs). |
The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in large vision-language models have led to remarkable progress in complex visual understanding across scientific and reasoning tasks. |
| Approach: | They evaluate 18 state-of-the-art vision-language models across 6 multimodal datasets with 3 distinct scoring functions and develop instruction-guided likelihood proxies for closed-source models lacking token-level logprob access. |
| Outcome: | The proposed model is able to achieve higher accuracy on multimodal benchmarks while performing poorer on reasoning tasks. |