Papers with WikiTQ

7 papers
TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data (2022.emnlp-main)

Copied to clipboard

Challenge: Existing auto-regressive pre-trained language models are challenged by recent emerging numerical reasoning datasets due to the error-prone implicit calculation.
Approach: They propose a pre-computation tool to pre-compute aggregation/arithmetic results for the table in advance, so they are handy and readily available for PLMs to answer numerical reasoning questions.
Outcome: The proposed model improves on TAT-QA and T5 and BART-large on multiple benchmarks.
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training (2026.findings-eacl)

Copied to clipboard

Challenge: Existing open-source datasets predominantly apply a single fixed extractor to all webpages.
Approach: They propose to take a Union over different extractors to improve model performance . they show that extractor choice can significantly impact downstream task performance based on content type .
Outcome: The proposed approach can increase the token yield of DCLM-Baseline by 71% while maintaining benchmark performance.
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition (2024.naacl-long)

Copied to clipboard

Challenge: Large language models struggle with large tables due to their limited input length . a novel method that decomposes tables into smaller and relevant sub-tables reduces the computational load on LLMs .
Approach: They propose a method that leverages text-to-SQL generation to decompose tables into smaller and relevant sub-tables . the method can reduce the input context length significantly, making it more scalable and efficient .
Outcome: The proposed method performs remarkably well on the WikiTQ benchmark and on the TabFact benchmark.
TaPas: Weakly Supervised Table Parsing via Pre-training (2020.acl-main)

Copied to clipboard

Challenge: Answering natural language questions over tables is often seen as a semantic parsing task.
Approach: They propose an approach to question answering over tables without generating logical forms by selecting table cells and optionally applying a corresponding aggregation operator.
Outcome: The proposed approach outperforms or rivals existing models on three different datasets and performs on par with the state-of-the-art on WikiSQL and WikiTQ.
Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search (2026.acl-long)

Copied to clipboard

Challenge: Existing pruning methods rely on sequential revisions and unreliable critique signals . Existing methods fail to detect the loss of answer-critical data .
Approach: They propose a table pruning framework which transforms table pruning to gold trajectory-supervised parallel search.
Outcome: The proposed framework outperforms the strongest baseline pruning framework by 3.2% on various tabular reasoning tasks.
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models with table-specific architectures and pre-training methods perform well on understanding table structures but lack table reasoning skills.
Approach: They propose to pre-train tables with table reasoning skills without complex architectures . they define 7 table reasoning skill, and then pre-teach them to generate tables .
Outcome: The proposed model improves on four tasks and is available on github.
TABARD: A Novel Benchmark for Tabular Anomaly Analysis, Reasoning and Detection (2025.findings-emnlp)

Copied to clipboard

Challenge: a new benchmark is constructed to evaluate the accuracy of large language models for tabular data . the benchmark uses direct, indirect, and Chain-of-Thought prompting .
Approach: They propose a framework that uses prompting, self-verification and constraint-based rule execution to improve accuracy.
Outcome: The proposed framework significantly improves accuracy and recall in tabular data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations