Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness. This blindspot leaves a logical alignment gap -- SFT models reach NLI entailment of only 0.05-0.22 despite producing fluent text. We propose RLearner-LLM with Hybrid-DPO: an automated preference pipeline that fuses a DeBERTa-v3 NLI signal with a verifier LLM score, removing human annotation while overcoming the "alignment tax" of single-signal optimization. Evaluated across five academic domains (Biology, Medicine, Law) with three base architectures (LLaMA-2-13B, Qwen3-8B, Gemma 4 E4B-it), RLearner-LLM yields up to 6x NLI improvement over SFT, with NLI gains in 11 of 15 cells and consistent answer-coverage gains. On Gemma 4 E4B-it (4.5B effective params), Hybrid-DPO lifts NLI in four of five domains (+11.9% to +2.4x) with faster inference across all five, scaling down to compact base models without losing the alignment-tax mitigation. Our Qwen3-8B RLearner-LLM wins 95% of pairwise comparisons against its own SFT baseline; GPT-4o-mini in turn wins 95% against our concise output -- alongside the 69% win the same judge gives a verbose SFT over our DPO model, this replicates verbosity bias on a frontier comparator and motivates logic-aware metrics (NLI, ACR) over LLM-as-a-judge for knowledge-intensive generation.
Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation
University of Bonn（波恩大学）；Lamarr-Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习和人工智能研究所）；Universitat Rovira i Virgili（罗维拉-维尔吉利大学）；Fraunhofer IAIS（弗劳恩霍夫智能分析和信息系统研究所）
MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
Stanford School of Medicine（斯坦福大学医学院）；Stanford School of Engineering（斯坦福大学工程学院）；Stanford University（斯坦福大学）；Stanford Health Care（斯坦福医疗保健）；Vanderbilt University School of Medicine（范德比尔特大学医学院）；Vanderbilt University Medical Center（范德比尔特大学医学中心）；Hospital Israelita Albert Einstein（以色列阿尔伯特·爱因斯坦医院）
GI-Bench: A Panoramic Benchmark Revealing the Knowledge-Experience Dissociation of Multimodal Large Language Models in Gastrointestinal Endoscopy Against Clinical Standards
Zhongshan Hospital, Fudan University（复旦大学附属中山医院）；School of Basic Medical Sciences, Fudan University（复旦大学基础医学院）；Microsoft Research Asia（微软亚洲研究院）；Data Science Institute, Imperial College London（帝国理工学院数据科学研究所）
