Hanyu Wang

Hongjin Su, Howard Yen, Mengzhou Xia et al.

Existing retrieval benchmarks primarily consist of information-seeking queries (e.g., aggregated questions from search engines) where keyword or semantic-based retrieval is usually sufficient. However, many complex real-world queries require in-depth reasoning to identify relevant documents that go beyond surface form matching. For example, finding documentation for a coding question requires understanding the logic and syntax of the functions involved. To better benchmark retrieval on such challenging queries, we introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents. Our dataset consists of 1,384 real-world queries spanning diverse domains, such as economics, psychology, mathematics, and coding. These queries are drawn from naturally occurring and carefully curated human data. Extensive evaluation reveals that even state-of-the-art retrieval models perform poorly on BRIGHT. The leading model on the MTEB leaderboard (Muennighoff et al., 2023) SFR-Embedding-Mistral (Meng et al., 2024), which achieves a score of 59.0 nDCG@10,1 produces a score of nDCG@10 of 18.3 on BRIGHT. We show that incorporating explicit reasoning about the query improves retrieval performance by up to 12.2 points. Moreover, incorporating retrieved documents from the top-performing retriever boosts question-answering performance. We believe that BRIGHT paves the way for future research on retrieval systems in more realistic and challenging settings.

Hanyu Wang, Emmanuel K. Tsinda, Anthony J. Dunn et al.

Surges that have been observed at different periods in the number of COVID-19 cases are associated with the emergence of multiple SARS-CoV-2 (Severe Acute Respiratory Virus) variants. The design of methods to support laboratory detection are crucial in the monitoring of these variants. Hence, in this paper, we develop a semi-automated method to design both forward and reverse primer sets to detect SARS-CoV-2 variants. To proceed, we train deep Convolution Neural Networks (CNNs) to classify labelled SARS-CoV-2 variants and identify partial genomic features needed for the forward and reverse Polymerase Chain Reaction (PCR) primer design. Our proposed approach supplements existing ones while promoting the emerging concept of neural network assisted primer design for PCR. Our CNN model was trained using a database of SARS-CoV-2 full-length genomes from GISAID and tested on a separate dataset from NCBI, with 98\% accuracy for the classification of variants. This result is based on the development of three different methods of feature extraction, and the selected primer sequences for each SARS-CoV-2 variant detection (except Omicron) were present in more than 95 \% of sequences in an independent set of 5000 same variant sequences, and below 5 \% in other independent datasets with 5000 sequences of each variant. In total, we obtain 22 forward and reverse primer pairs with flexible length sizes (18-25 base pairs) with an expected amplicon length ranging between 42 and 3322 nucleotides. Besides the feature appearance, in-silico primer checks confirmed that the identified primer pairs are suitable for accurate SARS-CoV-2 variant detection by means of PCR tests.

Akhmadillo Mamirov, Faiaz Azmain, Hanyu Wang

AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation from five frontier models (Gemini 3, Grok 4.1, Llama 4, GPT-5, and Claude 4.5) and 100 Hugging Face model cards, identifying 947 unique section names with extreme naming variation. Usage information alone appeared under 97 distinct labels. Using the EU AI Act Annex IV and the Stanford Transparency Index as baselines, we developed a weighted transparency framework with 8 sections and 23 subsections that prioritizes safety-critical disclosures (Safety Evaluation: 25%, Critical Risk: 20%) over technical specifications. We implemented an automated multi-agent pipeline that extracts documentation from public sources and scores completeness through LLM-based consensus. Evaluating 50 models across vision, multimodal, open-source, and closed-source systems cost less than $3 in total and revealed systematic gaps. Frontier labs (xAI, Microsoft, Anthropic) achieve approximately 80% compliance, while most providers fall below 60%. Safety-critical categories show the largest deficits: deception behaviors, hallucinations, and child safety evaluations account for 148, 124, and 116 aggregate points lost, respectively, across all evaluated models.

Hanyu Wang, Ruohan Xie, Yutong Wang et al.

Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their inability to synthesize new definitions. To tackle these issues, we present Aria (Agent for Retrieval and Iterative Autoformalization), a system for conjecture-level formalization in Lean that emulates human expert reasoning via a two-phase Graph-of-Thought process: recursively decomposing statements into a dependency graph and then constructing formalizations from grounded concepts. To ensure semantic correctness, we introduce AriaScorer, a checker that retrieves definitions from Mathlib for term-level grounding, enabling rigorous and reliable verification. We evaluate Aria on diverse benchmarks. On ProofNet, it achieves 91.6% compilation success rate and 68.5% final accuracy, surpassing previous methods. On FATE-X, a suite of challenging algebra problems from research literature, it outperforms the best baseline with 44.0% vs. 24.0% final accuracy. On a dataset of homological conjectures, Aria reaches 42.9% final accuracy while all other models score 0%.

Hanyu Wang, Emmanuel K. Tsinda, Anthony J. Dunn et al.

Motivation: PCR is more economical and quicker than Next Generation Sequencing for detecting target organisms, with primer design being a critical step. In epidemiology with rapidly mutating viruses, designing effective primers is challenging. Traditional methods require substantial manual intervention and struggle to ensure effective primer design across different strains. For organisms with large, similar genomes like Escherichia coli and Shigella flexneri, differentiating between species is also difficult but crucial. Results: We developed Primer C-VAE, a model based on a Variational Auto-Encoder framework with Convolutional Neural Networks to identify variants and generate specific primers. Using SARS-CoV-2, our model classified variants (alpha, beta, gamma, delta, omicron) with 98% accuracy and generated variant-specific primers. These primers appeared with >95% frequency in target variants and <5% in others, showing good performance in in-silico PCR tests. For Alpha, Delta, and Omicron, our primer pairs produced fragments <200 bp, suitable for qPCR detection. The model also generated effective primers for organisms with longer gene sequences like E. coli and S. flexneri. Conclusion: Primer C-VAE is an interpretable deep learning approach for developing specific primer pairs for target organisms. This flexible, semi-automated and reliable tool works regardless of sequence completeness and length, allowing for qPCR applications and can be applied to organisms with large and highly similar genomes.