Papers with TabFact
Understanding tables with intermediate pre-training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Textual entailment is well studied, but is less well studied for table enlargement . a new dataset of millions of examples is used to train the model . |
| Approach: | They adapt a table-based BERT model to recognize entailment from a dataset . they evaluate table pruning techniques as a pre-processing step to improve model efficiency . |
| Outcome: | The proposed model improves training and prediction efficiency at a moderate drop in accuracy. |
Large Language Models are few(1)-shot Table Reasoners (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent literature has shown that large language models are excellent few-shot reasoners to solve text reasoning tasks. |
| Approach: | They evaluated LLMs on popular table QA and fact verification datasets like WikiTableQuestion, FetaQA, TabFact, and FEVEROUS and found they are competent at complex reasoning over table structures. |
| Outcome: | The proposed models are more competent at complex reasoning over table structures than tuned T5-large models. |
TWT: Table with Written Text for Controlled Data-to-Text Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods output hallucinated text that is not faithful on TWT. |
| Approach: | They propose to generate text conditioned on the structured data and a prefix by leveraging pre-trained neural models. |
| Outcome: | The proposed approach outperforms state-of-the-art methods under automatic and human evaluation metrics. |
Table Fact Verification with Structure-Aware Transformer (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained models cannot be used to encode semi-structured data because of their nature. |
| Approach: | They propose a Structure-Aware Transformer which injects table structural information into mask . method could combine symbolic and linguistic reasoning, they propose . |
| Outcome: | The proposed method outperforms baseline on a large scale table verification dataset. |
NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. |
| Approach: | They propose a framework that normalizes web tables to support symbolic reasoning . they compare NormTab to a stand-alone framework that can normalize tabular data . |
| Outcome: | The proposed framework outperforms traditional models on symbolic reasoning tasks on tabular data. |
Weakly Supervised Semantic Parsing by Learning from Mistakes (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Weakly supervised semantic parsing requires searching consistent logical forms in a huge space and dealing with spurious logical form. |
| Approach: | They propose a learning framework that trains parsers via utterance-denotation pairs . they use utterrance-logical form pairs created from mistakes to bootstrap parser . |
| Outcome: | The proposed framework outperforms state-of-the-art methods on WikiSQL, TabFact and other datasets. |
PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training (2022.emnlp-main)
Copied to clipboard
| Challenge: | Table-based fact verification has attracted a lot of attention recently due to the lack of datasets that can be used to pre-train language models to be aware of common table operations. |
| Approach: | They propose a table-based fact verification tool that pre-trains language models to be aware of common table operations such as aggregating a column or comparing tuples. |
| Outcome: | The proposed method outperforms previous methods on two table-based fact verification datasets TabFact and SEM-TAB- FACTS. |
Table-based Fact Verification With Salience-aware Learning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for fact verification use tabular data with tokens, but training requires labeled training data. |
| Approach: | They propose a system that identifies token-level salience in the statement with probing-based saliency estimation. |
| Outcome: | The proposed system improves on TabFact benchmark by replacing non-salient terms with tokens. |
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. |
RePanda: Pandas-powered Tabular Verification and Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fact-checking tabular data rely on black-box models with opaque reasoning. |
| Approach: | They propose a structured fact verification approach that translates claims into executable pandas queries. |
| Outcome: | The proposed method outperforms existing methods and demonstrates strong OOD robustness. |