HypothesisMed: Inference-Time Answer Fusion and Structured Hypothesis-Space Reporting for Biomedical Question Answering

Biomedical question answering with large language models is commonly evaluated using answer accuracy, but answer accuracy alone does not indicate whether a model can produce parseable outputs, follow structured reliability instructions, recognize weak answer spaces, or avoid confident incorrect commitments. This paper presents HypothesisMed, an inference-time reliability pipeline for biomedical multiple-choice question answering. It combines direct, chain-of-thought, HypothesisMed-v3 prompting, and answer fusion. The final answer is selected by fusion, while HypothesisMed-v3 supplies SPACE labels and confidence information. SPACE labels mark the answer space as VALID, INCOMPLETE, or CONTRADICTED. We evaluate Qwen2.5-7B, Phi-4-mini, DeepSeek-R1-32B, and BioMistral-7B on MedQA, MedMCQA, and PubMedQA using 1,000 examples per dataset. The pipeline improves weighted accuracy over each model's best direct or chain-of-thought baseline while increasing parse and SPACE coverage. We also scale evaluation to Qwen2.5-7B and Phi-4-mini using 10,183 examples per model. Fusion improves Phi-4-mini accuracy from 0.4296 to 0.5192, while Qwen2.5-7B chain-of-thought remains slightly higher in answer accuracy. However, Qwen2.5-7B fusion achieves complete parse and SPACE coverage with much lower false commitment. A 12,000-example SPACE stress test shows answer-space diagnosis remains difficult, with SPACE accuracy of 0.3074 for Qwen2.5-7B and 0.4168 for Phi-4-mini. These results show that answer accuracy, parseability, structured reliability reporting, calibration behavior, and false-commitment behavior are separable capabilities. The main contribution is not a universal state-of-the-art claim, but a reproducible inference-time framework for evaluating biomedical question answering models as auditable workflow components under structured reliability constraints.

Gemma 4, Phi-4, and Qwen3: Accuracy-Efficiency Tradeoffs in Dense and MoE Reasoning Language Models

Mixture-of-experts (MoE) language models are often expected to offer better quality-efficiency tradeoffs than dense models because only a subset of parameters is activated per token, but the practical value of that advantage depends on end-to-end behavior under realistic inference constraints. We present a controlled empirical benchmark of seven recent reasoning-oriented instruction-tuned models spanning dense and MoE designs, namely Gemma-4-E2B, Gemma-4-E4B, Gemma-4-26B-A4B, Phi-4-mini-reasoning, Phi-4-reasoning, Qwen3-8B, and Qwen3-30B-A3B, evaluated on four benchmarks -- ARC-Challenge, GSM8K, Math Level 1-3, and TruthfulQA MC1 -- under three prompting strategies: zero-shot, chain-of-thought, and few-shot chain-of-thought. The study covers 8,400 total model-dataset-prompt evaluations and records accuracy, latency, peak GPU memory usage (VRAM), and an approximate floating-point operations (FLOPs)-per-token proxy. Across the weighted multi-task summary, Gemma-4-E4B with few-shot chain-of-thought achieved the best overall result, reaching weighted accuracy 0.675 with mean VRAM 14.9 GB, while Gemma-4-26B-A4B was close in accuracy at 0.663 but substantially more memory intensive at 48.1 GB. At the task level, Gemma models dominated ARC and Math, Phi models were strongest on TruthfulQA, and GSM8K showed the largest prompt sensitivity, including a sharp drop for Phi-4-reasoning from 0.67 under chain-of-thought to 0.11 under few-shot chain-of-thought. These results show that sparse activation alone does not guarantee the best practical operating point: observed accuracy-efficiency tradeoffs depend jointly on architecture, prompting protocol, and task composition. We release a reproducible benchmark pipeline, aggregated results, and paired statistical analyses to support deployment-oriented evaluation of reasoning LLMs under real resource constraints.

SlideChain: Semantic Provenance for Lecture Understanding via Blockchain Registration

Modern vision--language models (VLMs) are increasingly used to interpret and generate educational content, yet their semantic outputs remain challenging to verify, reproduce, and audit over time. Inconsistencies across model families, inference settings, and computing environments undermine the reliability of AI-generated instructional material, particularly in high-stakes and quantitative STEM domains. This work introduces SlideChain, a blockchain-backed provenance framework designed to provide verifiable integrity for multimodal semantic extraction at scale. Using the SlideChain Slides Dataset-a curated corpus of 1,117 medical imaging lecture slides from a university course-we extract concepts and relational triples from four state-of-the-art VLMs and construct structured provenance records for every slide. SlideChain anchors cryptographic hashes of these records on a local EVM (Ethereum Virtual Machine)-compatible blockchain, providing tamper-evident auditability and persistent semantic baselines. Through the first systematic analysis of semantic disagreement, cross-model similarity, and lecture-level variability in multimodal educational content, we reveal pronounced cross-model discrepancies, including low concept overlap and near-zero agreement in relational triples on many slides. We further evaluate gas usage, throughput, and scalability under simulated deployment conditions, and demonstrate perfect tamper detection along with deterministic reproducibility across independent extraction runs. Together, these results show that SlideChain provides a practical and scalable step toward trustworthy, verifiable multimodal educational pipelines, supporting long-term auditability, reproducibility, and integrity for AI-assisted instructional systems.

ALIVE: An Avatar-Lecture Interactive Video Engine with Content-Aware Retrieval for Real-Time Interaction

Traditional lecture videos offer flexibility but lack mechanisms for real-time clarification, forcing learners to search externally when confusion arises. Recent advances in large language models and neural avatars provide new opportunities for interactive learning, yet existing systems typically lack lecture awareness, rely on cloud-based services, or fail to integrate retrieval and avatar-delivered explanations in a unified, privacy-preserving pipeline. We present ALIVE, an Avatar-Lecture Interactive Video Engine that transforms passive lecture viewing into a dynamic, real-time learning experience. ALIVE operates fully on local hardware and integrates (1) Avatar-delivered lecture generated through ASR transcription, LLM refinement, and neural talking-head synthesis; (2) A content-aware retrieval mechanism that combines semantic similarity with timestamp alignment to surface contextually relevant lecture segments; and (3) Real-time multimodal interaction, enabling students to pause the lecture, ask questions through text or voice, and receive grounded explanations either as text or as avatar-delivered responses. To maintain responsiveness, ALIVE employs lightweight embedding models, FAISS-based retrieval, and segmented avatar synthesis with progressive preloading. We demonstrate the system on a complete medical imaging course, evaluate its retrieval accuracy, latency characteristics, and user experience, and show that ALIVE provides accurate, content-aware, and engaging real-time support. ALIVE illustrates how multimodal AI-when combined with content-aware retrieval and local deployment-can significantly enhance the pedagogical value of recorded lectures, offering an extensible pathway toward next-generation interactive learning environments.

N-ReLU: Zero-Mean Stochastic Extension of ReLU

Activation functions are fundamental for enabling nonlinear representations in deep neural networks. However, the standard rectified linear unit (ReLU) often suffers from inactive or "dead" neurons caused by its hard zero cutoff. To address this issue, we introduce N-ReLU (Noise-ReLU), a zero-mean stochastic extension of ReLU that replaces negative activations with Gaussian noise while preserving the same expected output. This expectation-aligned formulation maintains gradient flow in inactive regions and acts as an annealing-style regularizer during training. Experiments on the MNIST dataset using both multilayer perceptron (MLP) and convolutional neural network (CNN) architectures show that N-ReLU achieves accuracy comparable to or slightly exceeding that of ReLU, LeakyReLU, PReLU, GELU, and RReLU at moderate noise levels (sigma = 0.05-0.10), with stable convergence and no dead neurons observed. These results demonstrate that lightweight Gaussian noise injection offers a simple yet effective mechanism to enhance optimization robustness without modifying network structures or introducing additional parameters.

Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domain

Question-answering systems for Bengali have seen limited development, particularly in domain-specific applications. Leveraging advancements in natural language processing, this paper explores a fine-tuned BERT-Bangla model to address this gap. It presents the development of a question-answering system for Bengali using a fine-tuned BERT-Bangla model in a closed domain. The dataset was sourced from Khulna University of Engineering \& Technology's (KUET) website and other relevant texts. The system was trained and evaluated with 2500 question-answer pairs generated from curated data. Key metrics, including the Exact Match (EM) score and F1 score, were used for evaluation, achieving scores of 55.26\% and 74.21\%, respectively. The results demonstrate promising potential for domain-specific Bengali question-answering systems. Further refinements are needed to improve performance for more complex queries.