Metraipolis › archive › dc_a17eacc86ea2
HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding — arXiv:2610.34589
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34589
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:01:32.429Z
- SHA-256 of the archived text
dd2f104bc03ba3a5fda4ad26c292bc3a28091578ddba54bc4431f2a11810a61c- Stable URL of this page
https://metraipolis.com/documento/dc_a17eacc86ea2
How to cite
HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding — arXiv:2610.34589 — arXiv (en), https://arxiv.org/abs/2610.34589 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a17eacc86ea2 (Metraipolis archive dc_a17eacc86ea2, sha256 dd2f104bc03ba3a5fda4ad26c292bc3a28091578ddba54bc4431f2a11810a61c)
BibTeX
@misc{dca17eacc86ea2,
title = {HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding — arXiv:2610.34589},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34589},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a17eacc86ea2; sha256 dd2f104bc03ba3a5fda4ad26c292bc3a28091578ddba54bc4431f2a11810a61c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34589. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.34589 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:30.918Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).