# Data-Efficient Autoregressive Document Retrieval for Fact Verification

arXiv: https://arxiv.org/abs/2211.09388 · HTML: https://mlsanity.com/paper/2211.09388/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Builds on (most cited first, 23 of 23)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification](https://mlsanity.com/paper/2011.03088/) (2020)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [Autoregressive Search Engines: Generating Substrings as Document Identifiers](https://mlsanity.com/paper/2204.10628/) (2022)
- [UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification](https://mlsanity.com/paper/1809.01479/) (2018)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Multilingual Autoregressive Entity Linking](https://mlsanity.com/paper/2103.12528/) (2021)
- [Multi-task Retrieval for Knowledge-Intensive Tasks](https://mlsanity.com/paper/2101.00117/) (2021)
- [CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2208.07652/) (2022)
- [Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need](https://mlsanity.com/paper/2108.09346/) (2021)
- [Generative Multi-hop Retrieval](https://mlsanity.com/paper/2204.13596/) (2022)

## Built on by (most cited first, 6 of 6)

- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Evaluating Generative Ad Hoc Information Retrieval](https://mlsanity.com/paper/2311.04694/) (2023)
- [Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation](https://mlsanity.com/paper/2410.09350/) (2024)
- [A Survey of Generative Information Retrieval](https://mlsanity.com/paper/2406.01197/) (2024)
- [eXplainable Bayesian Multi-Perspective Generative Retrieval](https://mlsanity.com/paper/2402.02418/) (2024)
- [Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities](https://mlsanity.com/paper/2606.13397/) (2026)

## Abstract (arXiv)

Document retrieval is a core component of many knowledge-intensive natural language processing task formulations such as fact verification and question answering. Sources of textual knowledge, such as Wikipedia articles, condition the generation of answers from the models. Recent advances in retrieval use sequence-to-sequence models to incrementally predict the title of the appropriate Wikipedia page given a query. However, this method requires supervision in the form of human annotation to label which Wikipedia pages contain appropriate context. This paper introduces a distant-supervision method that does not require any annotation to train autoregressive retrievers that attain competitive R-Precision and Recall in a zero-shot setting. Furthermore we show that with task-specific supervised fine-tuning, autoregressive retrieval performance for two Wikipedia-based fact verification tasks can approach or even exceed full supervision using less than 1/4 of the annotated data indicating possible directions for data-efficient autoregressive retrieval.