Pith. sign in

REVIEW 5 cited by

General Table Question Answering via Answer-Formula Joint Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.12345 v3 pith:UEJSN4GR submitted 2025-03-16 cs.CL cs.AI

classification cs.CLcs.AI
keywords tabletableqatextttansweringquestiontabaftypescomplex
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Advanced table question answering (TableQA) methods prompt large language models (LLMs) to generate answer text, SQL query, Python code, or custom operation, which impressively improve the complex reasoning problems in the TableQA task. However, these methods lack the versatility to cope with specific question types or table structures. In contrast, the Spreadsheet Formula, the widely used and well-defined operation language for tabular data, has not been thoroughly explored to solve TableQA. In this paper, we first attempt to use the Formula as the executable representation for solving complex reasoning on tables with different structures. Specifically, we construct \texttt{FromulaQA}, a large Formula-annotated TableQA dataset from existing datasets. In addition, we propose \texttt{TabAF}, a general table answering framework to solve multiple types of tasks over multiple types of tables simultaneously, which decodes answers and Formulas with a single LLM backbone. Extensive experiments demonstrate the versatility and generalization of \texttt{TabAF}. Under the same model size, \texttt{TabAF} achieves new state-of-the-art performance on the WikiTableQuestion, HiTab, and TabFact.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Block-wise and cell-wise LoRA-MoE routers break static LoRA gradient conflicts on multi-context matrix tasks, with cell-level gates matching a global router on uniform shifts and beating it on heterogeneous ones.

  2. OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models

    cs.CY 2025-05 conditional novelty 4.0 of 10

    The paper advocates protecting and leveraging OpenReview's peer review corpus as a community asset for LLM-based review assistance, benchmarks, and alignment.

  3. The Anti-Ouroboros Effect: Emergent Resilience in Large Language Models from Recursive Selective Feedback

    cs.LG 2025-09 reject novelty 3.0 of 10

    A recursive fine-tuning study claims quality filtering reverses model collapse, but the paper's own data show the filtered model only matched its starting score.

  4. Cross-Model Semantics in Representation Learning

    cs.LG 2025-08 reject novelty 3.0 of 10

    The paper restates existing alignment metrics and claims, with no numerical evidence, that structured architectures show more stable cross-model representation geometry.

  5. The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web

    cs.CR 2025-07 reject novelty 3.0 of 10

    The paper presents a five-layer decentralized framework (Nanda) for agent discovery, trust scoring, and micropayments, but supports its deployment claims only with self-referential descriptions.

Pith tools