mlsanityData to 14 Oct 2026

Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extraction

arXiv 2409.14192 ↗First posted 21 Sep 2024cs.CL cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

Integrating structured knowledge from tabular formats poses significant challenges within natural language processing (NLP), mainly when dealing with complex, semi-structured tables like those found in the FeTaQA dataset. These tables require advanced methods to interpret and generate meaningful responses accurately. Traditional approaches, such as SQL and SPARQL, often fail to fully capture the semantics of such data, especially in the presence of irregular table structures like web tables. This paper addresses these challenges by proposing a novel approach that extracts triples straightforward from tabular data and integrates it with a retrieval-augmented generation (RAG) model to enhance the accuracy, coherence, and contextual richness of responses generated by a fine-tuned GPT-3.5-turbo-0125 model. Our approach significantly outperforms existing baselines on the FeTaQA dataset, particularly excelling in Sacre-BLEU and ROUGE metrics. It effectively generates contextually accurate and detailed long-form answers from tables, showcasing its strength in complex data interpretation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 21 Sep 2024.

Builds on

16 of 30 references.

References · 16

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  5. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  6. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  7. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  8. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  9. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 265
  10. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 178
  11. 2021FeTaQA: Free-form Table Question Answeringcited by 175
  12. 2023Large Language Models are Complex Table Parserscited by 28
4 more
  1. 2023Tab2KG: Semantic Table Interpretation with Lightweight Semantic Profilescited by 2
  2. 2020Computing Boundary Cycle of a Pseudo-Triangle Polygon from its Visibility Graphcited by 1
  3. 2023Enhancing the Performance of Automated Grade Prediction in MOOC using Graph Representation Learningcited by 1
  4. 2024RTF: Region-based Table Filling Method for Relational Triple Extractioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges
  2. 2026FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning
  3. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking
  4. 2024Beyond Extraction: Contextualising Tabular Data for Efficient Summarisation by Language Models
  5. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
  6. 2026Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
  7. 2023Rethinking Tabular Data Understanding with Large Language Models
  8. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition