Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucinated computer-processable rules. This paper introduces P4IR, a two-stage framework that uses supervised fine-tuning (SFT) to instill domain knowledge in an LLM, followed...
Jack Wei Lun Shi, Minghao Dang, Wawan Solihin et al.· 0 citations
Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across m...
Jiyoun Kim, Muhan Yeo, Eunhye Jang et al.· 0 citations
It is argued that a robust proof autoformalizer must remain faithful even for informal proofs that diverge from these idealized ones, and the first study on the robustness of proof autoformalization models is presented.
Adapting Large Language Models (LLMs) to specific tasks usually involves fine-tuning: Low-Rank Adaptation (LoRA) edits the weights, while soft prompting prepends trainable virtual tokens. Both change how an already-optimized model is served, so serving many task-specific adapters at high throughput requires adapter-awa...
Michal Chudoba, Sergey Alyaev, Petra Galuscakova et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
LLM deception is often evaluated through fabricated claims, explicit lies, or strategic concealment. Yet misleading communication can also arise from selectively presenting true facts, for example, by omitting adverse evidence, softening unfavorable details, emphasizing favorable information, or replacing precise quali...
This work introduces Code2LoRA, a hypernetwork framework that generates repository-specific LoRA adapters, effectively injecting repository knowledge with zero inference-time token overhead, and evaluates Code2LoRA against parameter-efficient fine-tuning baselines.
Liliana Hotsko, Yin-Xi Li, Yun-Tian Deng et al.· arXiv.org· 6 citations
This work shows that intermediate states surface salient entities early in the denoising trajectory, making them a useful lookahead signal for retrieval-augmented generation (RAG), and demonstrates that grounding generation in retrieved evidence sharply reduces inter-token dependence, making RAG particularly well suite...
Paul J. Jünger, Justin Lovelace, Lin-Xi Zhao et al.· arXiv.org· 2 citations· ⚡1
Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically disco...
Padmaja Jonnalagedda, Yuguang Yao, Xiang Gao et al.· 0 citations
Preference modeling aims to capture heterogeneous human values and increasingly relies on learning latent components to represent this variation without fine-grained supervision. What these components actually represent, however, is rarely examined. We audit Mixture-of-Experts (MoE) reward models along three rungs---se...
Yifan Wang, Jinyi Mu, Mayank Jobanputra et al.· 0 citations
Large language models (LLMs) are increasingly used to answer everyday health questions online, including whether someone can take another dose of an over-the-counter (OTC) medication. Yet this common safety-relevant setting remains underexplored in medical QA. Answering these questions requires checking previous doses,...
Maroof Kousar, Jinsung Han, Mohit Chandra et al.· 0 citations
OP-Mix (On-Policy Mix), a data mixing algorithm that operates across pretraining, midtraining, and instruction tuning, is introduced, suggesting a different view of language model training: not a sequence of distinct phases, but a single continuous process of learning from data.
Michael Y Hu, Apurva Gandhi, Kyunghyun Cho et al.· arXiv.org· 0 citations
Recent advances in large language models (LLMs) have led to the development of AI-powered tutoring systems that provide interactive support via dialogue. To enable these tutoring systems to provide personalized support, it is essential to assess student performance at each turn, motivating knowledge tracing (KT) in dia...
Shuyan Huang, Alexander Scarlatos, Jaewook Lee et al.· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
