arXiv subjects

Saman Sarker Joy

Publications and source records attributed to Saman Sarker Joy.

5 recordsLinked to original sources

arXiv2026

Do System One Decisions Add Up? A Study of Probabilistic Coherence

A decision model can give probabilities that sum to one for every question yet disagree with itself when the same decision is broken into smaller steps. We study this form of probabilistic coherence in Jev and the English Laya checkpoint, using 2,500 matched examples per system across TREC, CLINC150, and MASSIVE. Across 72,000 classification questions, we compare direct fine-label predictions with broad-category probabilities and predictions reconstructed through those categories. Both systems show substantial disagreement: mean category-level total variation ranges from 0.219 to 0.349 for Jev and from 0.424 to 0.689 for Laya, on a scale where zero means exact agreement. The consequences differ sharply. On CLINC150, reconstruction reduces Jev's accuracy by 22.9 percentage points (paired 95% bootstrap interval: [-24.9, -20.9]) and improves Laya's by 21.3 points ([18.0, 24.5]). The same directions hold across all three datasets, with all six unadjusted accuracy-change intervals excluding zero. Improved accuracy can also accompany less reliable confidence: on MASSIVE, Laya gains 9.2 accuracy points while its expected calibration error rises from 0.046 to 0.124. Error analysis identifies both broad-category mistakes and within-category confusions. These findings show why decision systems need joint evaluation of accuracy, confidence calibration, and probability coherence in the workflow used by an application.

cs.CL↗

arXiv2026

Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation

Medical vision-language models still struggle to match radiologists' attention and to verbalize findings with explicit spatial grounding. We address this gap with a two-stage multimodal framework for chest X-ray interpretation built on the MIMIC-Eye dataset. In the first stage introduces a gaze-token classifier that fuses image patches, bounding-box masks, transcription embeddings, and radiologist fixations. A curriculum-scheduled, trust-calibrated composite loss supervises the gaze token, boosting both accuracy and spatial alignment. Adding fixation supervision raises AUC 4.4% and F1 13.3%, and Pearson correlation rises to 0.306, confirming clinically relevant focus. In stage 2, classifier predictions are translated into region-specific diagnostic sentences. Confidence-weighted keywords are extracted, mapped to 17 thoracic regions through an expert dictionary, and expanded with a prompted large language model, boosting clinical-term BERTScore and ROUGE scores over keyword baselines. All components are toggle-able for ablation, and the full pipeline is reproducible, offering a new benchmark for interpretable, gaze-aware chest-X-ray analysis. Integrating eye-tracking signals demonstrably enhances both diagnostic accuracy and the transparency of generated reports.

cs.CV↗

arXiv2026

MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs

Large language models (LLMs) are increasingly used for health-related advice. Existing research measures their safety with static questions rather than pressured patient-facing conversations. We introduce MedPRESS, a multi-turn benchmark for measuring patient-pressure-induced sycophancy in LLMs. MedPRESS contains 600 medically grounded five-turn dialogues across three scenario families: medication and treatment demand, personal health self-care, and symptom triage and care resistance. Each dialogue begins with a health query and escalates through personal experience, social proof, external evidence claims, and direct adversarial challenge. We evaluate 20 LLMs across general, medical-domain, lightweight, large, open-weight, and proprietary families using structured judging and safety-focused metrics. Results show that models frequently shift toward unsafe agreement under repeated patient pressure, with substantial variation across model families, model scale, and prompt type. Anti-sycophancy prompting improves robustness for several models, but does not eliminate unsafe agreement. MedPRESS highlights a critical gap in medical LLM evaluation: safe medical knowledge is not enough unless models can maintain it under conversational pressure.

cs.CL↗

arXiv2026

BnMMLU: Measuring Massive Multitask Language Understanding in Bengali

Large-scale multitask benchmarks have driven rapid progress in language modeling, yet most emphasize high-resource languages such as English, leaving Bengali underrepresented. We present BnMMLU, a comprehensive benchmark for measuring massive multitask language understanding in Bengali. BnMMLU spans 41 domains across STEM, humanities, social sciences, and general knowledge, and contains 134,375 multiple-choice question-option pairs--the most extensive Bengali evaluation suite to date. The dataset preserves mathematical content via MathML, and includes BnMMLU-HARD, a compact subset constructed from questions most frequently missed by top systems to stress difficult cases. We benchmark 24 model variants across 11 LLM families, spanning open-weights general/multilingual, Bengali-centric open-weights, and proprietary models, covering multiple parameter scales and instruction-tuned settings. We evaluate models under standardized protocols covering two prompting styles (Direct vs. Chain-of-Thought) and two context regimes (0-shot vs. 5-shot), reporting accuracy consistently across families. Our analysis highlights persistent gaps in reasoning and application skills and indicates sublinear returns to scale across model sizes. We release the dataset and evaluation templates to support rigorous, reproducible assessment of Bengali language understanding and to catalyze progress in multilingual NLP.

cs.CL↗

arXiv2024

Gazetteer-Enhanced Bangla Named Entity Recognition with BanglaBERT Semantic Embeddings K-Means-Infused CRF Model

Named Entity Recognition (NER) is a sub-task of Natural Language Processing (NLP) that distinguishes entities from unorganized text into predefined categorization. In recent years, a lot of Bangla NLP subtasks have received quite a lot of attention; but Named Entity Recognition in Bangla still lags behind. In this research, we explored the existing state of research in Bangla Named Entity Recognition. We tried to figure out the limitations that current techniques and datasets face, and we would like to address these limitations in our research. Additionally, We developed a Gazetteer that has the ability to significantly boost the performance of NER. We also proposed a new NER solution by taking advantage of state-of-the-art NLP tools that outperform conventional techniques.

cs.CL↗