arXiv cs — 2026-04-15
- VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answe...
  https://arxiv.org/abs/2604.08549
- Unbiased Rectification for Sequential Recommender Systems Under Fake Orders
  https://arxiv.org/abs/2604.08550
- Self-Sovereign Agent
  https://arxiv.org/abs/2604.08551
- Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Con...
  https://arxiv.org/abs/2604.08552
- GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback
  https://arxiv.org/abs/2604.08553
- Drift and selection in LLM text ecosystems
  https://arxiv.org/abs/2604.08554
- SynDocDis: A Metadata-Driven Framework for Generating Synthetic Physician Dis...
  https://arxiv.org/abs/2604.08555
- EMA Is Not All You Need: Mapping the Boundary Between Structure and Content i...
  https://arxiv.org/abs/2604.08556
- Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Langu...
  https://arxiv.org/abs/2604.08557
- WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregress...
  https://arxiv.org/abs/2604.08558
- Medical Reasoning with Large Language Models: A Survey and MR-Bench
  https://arxiv.org/abs/2604.08559
- Uncertainty Estimation for the Open-Set Text Classification systems
  https://arxiv.org/abs/2604.08560

...and 893 more

> **VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering**
> 
> View PDF HTML (experimental) Abstract:We introduce VerifAI, an open-source expert system for biomedical question answering that integrates retrieval-augmented generation (RAG) with a novel post-hoc claim verification mechanism. Unlike standard RAG systems, VerifAI ensures factual consistency by decomposing generated answers into atomic claims and validating them against retrieved evidence using a fine-tuned natural language inference (NLI) engine. The system comprises three modular components: (1) a hybrid Information Retrieval (IR) module optimized for biomedical queries (MAP@10 of 42.7%), (2) a citation-aware Generative Component fine-tuned on a custom dataset to produce referenced answers, and (3) a Verification Component that detects hallucinations with state-of-the-art accuracy, outperforming GPT-4 on the HealthVer benchmark. Evaluations demonstrate that VerifAI significantly reduces hallucinated citations compared to zero-shot baselines and provides a transparent, verifiable lineage for every claim. The full pipeline, including code, models, and datasets, is open-sourced to facilitate reliable AI deployment in high-stakes domains. Subjects: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2604.08549 [cs.IR] (or arXiv:2604.08549v1 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2604.08549 arXiv-issued DOI via DataCite Journal reference: Sumitted to IEEE Access,2026 Submission history From: Nikola Milošević Dr [view email] [v1] Fri, 16 Jan 2026 09:08:17 UTC (2,978 KB)

tl;dr: VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering. Unbiased Rectification for Sequential Recommender Systems Under Fake Orders. Self-Sovereign Agent. Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained Approach. GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback.