mlsanityData to 14 Oct 2026

DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data

arXiv 2211.12668 ↗First posted 23 Nov 2022cs.CL cs.AI cs.IRcited by 10

Not on the map. Why?

Abstract (arXiv)

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question, state-of-the-art methods use a retriever-generator pipeline. However, their retrieval results are static, while different generation steps may rely on different sentences. To attend to the retrieved information that is relevant to each generation step, in this paper, we propose DyRRen, an extended retriever-reranker-generator framework where each generation step is enhanced by a dynamic reranking of retrieved sentences. It outperforms existing baselines on the FinQA dataset.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

27 of 46 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2020Longformer: The Long-Document Transformercited by 3,413
  4. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  5. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  6. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  7. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  8. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  9. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  10. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
  11. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  12. 2020Open Question Answering over Tables and Textcited by 163
15 more
  1. 2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 155
  2. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 121
  3. 2020Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Modelscited by 110
  4. 2021Generate & Rank: A Multi-task Framework for Math Word Problemscited by 82
  5. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  6. 2019Neural Module Networks for Reasoning over Textcited by 66
  7. 2021MATE: Multi-view Attention for Table Transformer Efficiencycited by 54
  8. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  9. 2021Neural-Symbolic Solver for Math Word Problems with Auxiliary Taskscited by 38
  10. 2020Question Directed Graph Attention Network for Numerical Reasoning over Textcited by 35
  11. 2020RikiNet: Reading Wikipedia Pages for Natural Question Answeringcited by 21
  12. 2021TSQA: Tabular Scenario Based Question Answeringcited by 21
  13. 2022Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decodercited by 17
  14. 2021Recall and Learn: A Memory-augmented Solver for Math Word Problemscited by 13
  15. 2022OPERA:Operation-Pivoted Discrete Reasoning over Textcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 5; 2025: 2.

10 papers.

  1. 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Datacited by 19
  2. 2023S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answeringcited by 17
  3. 2022APOLLO: An Optimized Training Approach for Long-form Numerical Reasoningcited by 8
  4. 2024FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Modelscited by 6
  5. 2024FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipelinecited by 6
  6. 2024CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAGcited by 6
  7. 2023Retrieval-Augmented Chain-of-Thought in Semi-structured Domainscited by 4
  8. 2024FormulaReasoning: A Dataset for Formula-Based Numerical Reasoningcited by 2
  9. 2025LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Modelscited by 2
  10. 2025CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generationcited by 1