collaborators

11 papers

cs.AI2026

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

Ridwan Mahbub, Mohammed Saidul Islam, Md Tahmid Rahman Laskar +3

Information visualizations are widely used to communicate patterns, trends, and outliers, yet deceptive design choices-such as truncated or inverted axes, distorted aspect ratios,…

cs.CL2026

Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models

Mir Tafseer Nayeem, Davood Rafiei

Large language models (LLMs) are increasingly deployed in high-stakes domains, yet they expose only limited language settings, most notably "English (US)," despite the global diver…

cs.CL2026

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

Sawsan Alqahtani, Mir Tafseer Nayeem, Md Tahmid Rahman Laskar +2

Tokenization underlies every large language model, yet it remains an under-theorized and inconsistently designed component. Common subword approaches such as Byte Pair Encoding (BP…

cs.CL2025

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

Mir Tafseer Nayeem, Davood Rafiei

We study the problem of opinion highlights generation from large volumes of user reviews, often exceeding thousands per entity, where existing methods either fail to scale or produ…

cs.CL2025

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

Mir Tafseer Nayeem, Sawsan Alqahtani, Md Tahmid Rahman Laskar +2

Tokenization is a crucial but under-evaluated step in large language models (LLMs). The standard metric, fertility (the average number of tokens per word), captures compression eff…

cs.CL2025

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

Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Ridwan Mahbub +7

Large Vision-Language Models (LVLMs) with only 7B parameters have shown promise as automated judges in chart comprehension tasks. However, tiny models (<=2B parameters) still perfo…