mlsanityData to 7 Oct 2026

Visconde: Multi-document QA with GPT-3 and Neural Reranking

arXiv 2212.09656 ↗First posted 19 Dec 2022cs.CL cs.IRcited by 23

Not on the map. Why?

Abstract (arXiv)

This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate. The first step decomposes the question into simpler questions using a few-shot large language model (LLM). Then, a state-of-the-art search engine is used to retrieve candidate passages from a large collection for each decomposed question. In the final step, we use the LLM in a few-shot setting to aggregate the contents of the passages into the final answer. The system is evaluated on three datasets: IIRC, Qasper, and StrategyQA. Results suggest that current retrievers are the main bottleneck and that readers are already performing at the human level as long as relevant passages are provided. The system is also shown to be more effective when the model is induced to give explanations before answering a question. Code is available at urlhttps://github.com/neuralmind-ai/visconde.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

31 of 37 references.

References · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  9. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  10. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  11. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  12. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
19 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  2. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  3. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  4. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
  5. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  6. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  7. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  8. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  9. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  10. 2022Faithful Reasoning Using Large Language Modelscited by 130
  11. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  12. 2022UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Trainingcited by 57
  13. 2020IIRC: A Dataset of Incomplete Information Reading Comprehension Questionscited by 52
  14. 2019Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answeringcited by 48
  15. 2022Questions Are All You Need to Train a Dense Passage Retrievercited by 47
  16. 2019Multi-Hop Paragraph Retrieval for Open-Domain Question Answeringcited by 34
  17. 2022Adapting Pretrained Text-to-Text Models for Long Text Sequencescited by 21
  18. 2021Boosting Search Engines with Interactive Agentscited by 19
  19. 2022Zero-Shot Retrieval with Search Agents and Hybrid Environmentscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 10; 2025: 2; 2026: 2.

23 papers.

Sort:

By area:

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  2. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  3. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  4. 2024The Chronicles of RAG: The Retriever, the Chunk and the Generatorcited by 34
  5. 2023PDFTriage: Question Answering over Long, Structured Documentscited by 29
  6. 2024Characterizing LLM Abstention Behavior in Science QA with Context Perturbationscited by 26
  7. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answeringcited by 14
  8. 2023Drilling Down into the Discourse Structure with LLMs for Long Document Question Answeringcited by 8
  9. 2023Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Modelscited by 6
  10. 2024FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipelinecited by 6
  11. 2023Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answeringcited by 5
  12. 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalcited by 5
11 more
  1. 2023LitSumm: Large language models for literature summarisation of non-coding RNAscited by 3
  2. 2024Towards Self-Contained Answers: Entity-Based Answer Rewriting in Conversational Searchcited by 3
  3. 2024Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contextscited by 3
  4. 2025NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answeringcited by 3
  5. 2024Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answeringcited by 2
  6. 2026EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memorycited by 2
  7. 2023MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answeringcited by 1
  8. 2024Explaining Mixtures of Sources in News Articlescited by 1
  9. 2023Evaluation of Faithfulness Using the Longest Supported Subsequencecited by 0
  10. 2024INACIA: Integrating Large Language Models in Brazilian Audit Courts: Opportunities and Challengescited by 0
  11. 2026Gradually Excavating External Knowledge for Implicit Complex Question Answeringcited by 0