arXiv cs.AI· Hossein Sholehrasa, Mohammadhossein Amini, Doina Caragea, Remya Ampadi Ramachandran, Dan Wu, Zihang Shi, Zelin Li, Lindsey Hulbert, Eder Martinez, Xuan Xu, Majid Jaberi-Douraki·· 3 小时前AI 评分36
HARP-LoRA：面向科学表格理解的层级条件秩投影低秩适配方法
HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding
AI 导读
研究者提出 HARP-LoRA，一种用于科学表格理解的层级条件秩投影 LoRA 微调方法，利用行列表头层级构建 token 特有的内在表示来约束低秩降投影。
正文 · 原文
Authors:Hossein Sholehrasa, Mohammadhossein Amini, Doina Caragea, Remya Ampadi Ramachandran, Dan Wu, Zihang Shi, Zelin Li, Lindsey Hulbert, Eder Martinez, Xuan Xu, Majid Jaberi-Douraki
Abstract:Tabular data is widely used in scientific applications, where complex layouts, including multi-level headers, merged cells, captions, and footnotes, make information extraction difficult. This is particularly important in pharmacokinetics (PK), where values must be correctly associated with the drug, species, dose, administration route, unit, and experimental condition. Parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA) reduce adaptation cost but do not explicitly incorporate relationships between table values and surrounding headers. We introduce HARP-LoRA, a hierarchy-conditioned rank projection method for low-rank adaptation in scientific table understanding. HARP-LoRA extends projected LoRA by constructing token-specific intrinsic representations from the row- and column-header hierarchies of each data token. These representations condition the low-rank down-projection, incorporating hierarchical context while keeping the pretrained model and random projection tensors frozen. We evaluate HARP-LoRA on 950 manually annotated PK tables from 587 scientific articles and on WikiTableQuestions (WikiTQ) using Llama~3.2 3B, Llama~3.1 8B, and Gemma~3 27B. With Llama~3.1 8B, HARP-LoRA achieves a PK F1-score of 57.64\% and WikiTQ accuracy of 53.15\%, improving over LoRA by 1.42 and 6.56 points, respectively. With Gemma~3 27B, it achieves the best PK F1-score of 70.63\% and WikiTQ accuracy of 56.87\%. These results use only 172K, 197K, and 547K trainable parameters, far fewer than LoRA and TableLoRA. Overall, conditioning lightweight adapters on table-header hierarchies improves extraction from scientific tables and reasoning over flatter general-domain tables while maintaining parameter efficiency. Code is available at: this https URL
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.34589 [cs.CL] |
| (or arXiv:2610.34589v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34589 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hossein Sholehrasa [view email]
[v1]
Sun, 25 Oct 2026 21:40:59 UTC (1,133 KB)
来源：arXiv cs.AI · arxiv.org