Metraipolis › archive › dc_99ffadda2d6d

PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding — arXiv:2608.24082

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24082
License (as archived)
CC0-1.0
Archived
2026-10-18T06:18:00.329Z
SHA-256 of the archived text
183688a72dcd7076b7778f5f29c981f94ebd8072c488178e511b918af05c587d
Stable URL of this page
https://metraipolis.com/documento/dc_99ffadda2d6d

How to cite

PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding — arXiv:2608.24082 — arXiv (en), https://arxiv.org/abs/2608.24082 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99ffadda2d6d (Metraipolis archive dc_99ffadda2d6d, sha256 183688a72dcd7076b7778f5f29c981f94ebd8072c488178e511b918af05c587d)
BibTeX
@misc{dc99ffadda2d6d,
  title = {PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding — arXiv:2608.24082},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24082},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99ffadda2d6d; sha256 183688a72dcd7076b7778f5f29c981f94ebd8072c488178e511b918af05c587d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24082. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effectiveness degrades as tables grow in size and complexity due to irrelevant context and difficulty localizing the evidence required for reasoning. Existing approaches typically reason over either the full table or a single reduced view, which can still obscure important row-column relationships. We introducePARTAB (Partition-Aware Reasoning overTables), a framework that constructs a structured evidence interface between the LLM and the table. PARTAB represents query-relevant evidence as semantically coherent, row-linked table regions and performs hierarchical selection over column groups and row-level partitions before composing the selected evidence for answer generation. We evaluate PARTAB on multiple table reasoning benchmarks, covering question answering, fact verification, and numerical reasoning. PARTAB consistently improves over full-table prompting and several recent table reasoning methods, achieving strong performance on WikiTableQuestions and TabFact while remaining competitive on numerical reasoning. Additional analyses show that semantic partitioning and targeted evidence selection improve evidence localization, substantially reduce the reasoning context, and provide larger benefits on complex tables. These results demonstrate the value of structured, partition aware evidence construction for scalable table reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.24082 — 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 2026-10-18T06:17:29.354Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).