mlsanityData to 14 Oct 2026

RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering

arXiv 2305.17041 ↗First posted 26 May 2023cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Open-Domain Question Answering (ODQA) systems necessitate a reader model capable of generating answers by simultaneously referring to multiple passages. Although representative models like Fusion-in-Decoder (FiD) have been proposed to address this challenge, these systems can inadvertently rely on spurious features instead of genuine causal relationships between the question and the passages to generate answers. To counter this problem, we introduce the Rational Fusion-in-Decoder (RFiD) model. Our model leverages the encoders of FiD to differentiate between causal relationships and spurious features, subsequently guiding the decoder to generate answers informed by this discernment. Experimental results on two ODQA datasets, Natural Questions (NQ) and TriviaQA (TQ), demonstrate that our model surpasses previous methods, achieving improvements of up to 1.5 and 0.7 in Exact Match scores on NQ, and exhibits an enhanced ability to identify causal relationships.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 24 of its 31 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

24 of 31 references.

References · 24

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  6. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  7. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  8. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  9. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  10. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  11. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  12. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 113
12 more
  1. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  2. 2020Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactualscited by 67
  3. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 67
  4. 2020Explaining The Efficacy of Counterfactually Augmented Datacited by 65
  5. 2021Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?cited by 62
  6. 2022Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasetscited by 54
  7. 2021Evidentiality-guided Generation for Knowledge-Intensive NLP Taskscited by 40
  8. 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
  9. 2021Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysiscited by 30
  10. 2022A Rationale-Centric Framework for Human-in-the-loop Machine Learningcited by 27
  11. 2022Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answeringcited by 22
  12. 2022FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognitioncited by 7

Built on by

Cited by year

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

4 papers.

  1. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 316
  2. 2024Enhancing Question Answering for Enterprise Knowledge Bases using Large Language Modelscited by 7
  3. 2025Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAGcited by 5
  4. 2025Prompting is not Enough: Exploring Knowledge Integration and Controllable Generationcited by 2