Publications

Profiles

Google Scholar ACL Anthology DBLP

* Equal contribution

Preprints & Working Papers

WhoseBench convention profiles across eleven text benchmarks

arXiv

Whose Data, Whose Benchmark? A User-Centric Framework for Auditing Evaluation Resources

Preprint (2026)

Mir Tafseer Nayeem and Davood Rafiei

Paper Website Code

Structural bias study overview across the LLM pipeline

arXiv

How Does "English (US)" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline

Preprint (2026)

Mir Tafseer Nayeem and Davood Rafiei

Paper Website Code Dataset

NameTrace overview of lexical name support and concept accessibility

arXiv

Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models

Preprint (2026)

Mir Tafseer Nayeem and Davood Rafiei

Paper Website Code Dataset

CineSubBench overview of multilingual film subtitle evaluation

arXiv

CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles

Preprint (2026)

Mir Tafseer Nayeem, Susmoy Chakraborty, and Davood Rafiei

Paper Website Code Dataset

Examples from the VisDeception chart-deception taxonomy

arXiv

Chart Deception in Vision-Language Models: From Vulnerability to Mitigation

Preprint (2026)

Ridwan Mahbub, Mohammed Saidul Islam, Md Tahmid Rahman Laskar*, Mizanur Rahman*, Mir Tafseer Nayeem*, and Enamul Hoque

Paper Code Dataset

2026

EACL 2026

Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models

Published at EACL 2026(Main) Oral

Mir Tafseer Nayeem*, Sawsan Alqahtani*, Md Tahmid Rahman Laskar, Tasnim Mohiuddin, and M Saiful Bari

Paper

FontReason framework for typographic variation and robustness evaluation

NeurIPS 2026 Workshop

What Happens When the Font Changes? A Controlled Study of Typographic Robustness in Vision-Language Models

Published at NeurIPS 2026(Workshop)

Mohammed Saidul Islam*, Md Tahmid Rahman Laskar*, Mir Tafseer Nayeem*, Shumaita Binte Burhan, Raian Rahman, Morsalina, Shafiq Joty, Enamul Hoque, and Jimmy Huang

Paper

ACL 2026

Lost in Translation: Do LVLM Judges Generalize Across Languages?

Published at ACL 2026(Findings)

Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Mir Tafseer Nayeem, Amran Bhuiyan, Mizanur Rahman, Shafiq Joty, Enamul Hoque, and Jimmy Huang

Paper Code Dataset

ROBUSTCHART360 examples across six chart-understanding robustness tasks

EMNLP 2026

From Benchmarks to Real-World Use: Evaluating the Robustness of Vision-Language Models for Chart Understanding

Published at EMNLP 2026(Industry Track)

Awal Ahmed Fime*, Mohammed Saidul Islam*, Md Tahmid Rahman Laskar, Md Zarif Hossain, Ridwan Mahbub, Mir Tafseer Nayeem, Mizanur Rahman, Ahmed Imteaj, and Enamul Hoque Prince

Paper

SurveyAgent-HKA pipeline from literature retrieval through survey evaluation

KBS 2026

SurveyAgent-HKA: A Multi-Agent Framework for Scientific Survey Generation with LLMs and Human Knowledge Augmentation

Published in Knowledge-Based Systems

Tong Bao, Mir Tafseer Nayeem, Yi Zhao, Davood Rafiei, and Chengzhi Zhang

Paper Code

RL-MR phase-wise pipeline from task encoding to budget-aware model ranking

AACL 2026

RL-MR: Reinforcement Learning based Budget-Aware Sequential Pretrained Model Ranking

Published at AACL 2026(Main) Oral

Saddam Mukta, Md. Ahashan Habib, Mir Tafseer Nayeem, and Md Adnanul Islam

2025

COLM 2025

OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews

Published at COLM 2025

Mir Tafseer Nayeem and Davood Rafiei

Paper Website

NeurIPS 2025 Workshop

Beyond Fertility: Analyzing STRR as a Metric for Multilingual Tokenization Evaluation

Published at NeurIPS 2025(Workshop)

Mir Tafseer Nayeem*, Sawsan Alqahtani*, Md Tahmid Rahman Laskar, Tasnim Mohiuddin, and M Saiful Bari

Paper Code Poster

EMNLP 2025

SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models

Published at EMNLP 2025(Main) Oral

Tong Bao, Mir Tafseer Nayeem, Davood Rafiei, and Chengzhi Zhang

Paper Code Slides Poster

From Charts to Fair Narratives thumbnail

EMNLP 2025

From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text

Published at EMNLP 2025(Main)

Ridwan Mahbub*, Mohammed Saidul Islam*, Mir Tafseer Nayeem, Md Tahmid Rahman Laskar, Mizanur Rahman, Shafiq Joty, and Enamul Hoque

Paper Slides Poster

EMNLP 2025

Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices

Published at EMNLP 2025(Industry Track)

Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Ridwan Mahbub, Mizanur Rahman, Amran Bhuiyan, Israt Jahan, Mir Tafseer Nayeem, Shafiq Joty, Enamul Hoque, and Jimmy Huang

Paper Code

IEEE VIS 2025

The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language Models

Published at IEEE VIS 2025 Oral

🏆 Best Short Paper Award

Ridwan Mahbub, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Mizanur Rahman, Mir Tafseer Nayeem, and Enamul Hoque

Paper Code Media Coverage

ACL 2025

Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?

Published at ACL 2025(Industry Track)

Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Ridwan Mahbub, Ahmed Masry, Mizanur Rahman, Amran Bhuiyan, Mir Tafseer Nayeem, Shafiq Joty, Enamul Hoque, and Jimmy Huang

Paper Code