# GERE: Generative Evidence Retrieval for Fact Verification

arXiv: https://arxiv.org/abs/2204.05511 · HTML: https://mlsanity.com/paper/2204.05511/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 12 Apr 2022.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [A Deep Relevance Matching Model for Ad-hoc Retrieval](https://mlsanity.com/paper/1711.08611/) (2017)
- [Combining Fact Extraction and Verification with Neural Semantic Matching Networks](https://mlsanity.com/paper/1811.07039/) (2018)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [Fine-grained Fact Verification with Kernel Graph Attention Network](https://mlsanity.com/paper/1910.09796/) (2019)
- [GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification](https://mlsanity.com/paper/1908.01843/) (2019)
- [CEDR: Contextualized Embeddings for Document Ranking](https://mlsanity.com/paper/1904.07094/) (2019)
- [Reasoning Over Semantic-Level Graph for Fact Checking](https://mlsanity.com/paper/1909.03745/) (2019)
- [UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification](https://mlsanity.com/paper/1809.01479/) (2018)
- [BERT for Evidence Retrieval and Claim Verification](https://mlsanity.com/paper/1910.02655/) (2019)
- [Revealing the Importance of Semantic Retrieval for Machine Reading at Scale](https://mlsanity.com/paper/1909.08041/) (2019)
- [Rethinking Search: Making Domain Experts out of Dilettantes](https://mlsanity.com/paper/2105.02274/) (2021)
- [TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification](https://mlsanity.com/paper/1808.03465/) (2018)
- [Context Attentive Document Ranking and Query Suggestion](https://mlsanity.com/paper/1906.02329/) (2019)
- [Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification](https://mlsanity.com/paper/2010.05111/) (2020)
- [Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference](https://mlsanity.com/paper/1904.12104/) (2019)

## Built on by (most cited first, 30 of 38)

- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [A Survey on Retrieval-Augmented Text Generation for Large Language Models](https://mlsanity.com/paper/2404.10981/) (2024)
- [CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2208.07652/) (2022)
- [Claim Verification in the Age of Large Language Models: A Survey](https://mlsanity.com/paper/2408.14317/) (2024)
- [Generative Multi-Modal Knowledge Retrieval with Large Language Models](https://mlsanity.com/paper/2401.08206/) (2024)
- [Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding](https://mlsanity.com/paper/2404.14600/) (2024)
- [Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence](https://mlsanity.com/paper/2305.03507/) (2023)
- [A Survey of Generative Search and Recommendation in the Era of Large Language Models](https://mlsanity.com/paper/2404.16924/) (2024)
- [The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval](https://mlsanity.com/paper/2503.14828/) (2025)
- [Multimodal Large Language Models to Support Real-World Fact-Checking](https://mlsanity.com/paper/2403.03627/) (2024)
- [Evaluating Generative Ad Hoc Information Retrieval](https://mlsanity.com/paper/2311.04694/) (2023)
- [CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2402.16767/) (2024)
- [AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2409.01579/) (2024)
- [Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval](https://mlsanity.com/paper/2504.05181/) (2025)
- [On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective](https://mlsanity.com/paper/2306.12756/) (2023)
- [Are Large Language Models Good Fact Checkers: A Preliminary Study](https://mlsanity.com/paper/2311.17355/) (2023)
- [Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search](https://mlsanity.com/paper/2402.07742/) (2024)
- [List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation](https://mlsanity.com/paper/2402.02764/) (2024)
- [Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation](https://mlsanity.com/paper/2410.09350/) (2024)
- [Unsupervised Pretraining for Fact Verification by Language Model Distillation](https://mlsanity.com/paper/2309.16540/) (2023)
- [Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.02993/) (2026)
- [A Survey of Generative Information Retrieval](https://mlsanity.com/paper/2406.01197/) (2024)
- [Fact or Fiction? Improving Fact Verification with Knowledge Graphs through Simplified Subgraph Retrievals](https://mlsanity.com/paper/2408.07453/) (2024)
- [TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification](https://mlsanity.com/paper/2503.15289/) (2025)
- [Exploring Training and Inference Scaling Laws in Generative Retrieval](https://mlsanity.com/paper/2503.18941/) (2025)
- [A Comprehensive Dataset for Human vs. AI Generated Text Detection](https://mlsanity.com/paper/2510.22874/) (2025)
- [RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation](https://mlsanity.com/paper/2312.10466/) (2023)
- [Classifying Human-Generated and AI-Generated Election Claims in Social Media](https://mlsanity.com/paper/2404.16116/) (2024)
- [GenProve: Learning to Generate Text with Fine-Grained Provenance](https://mlsanity.com/paper/2601.04932/) (2026)
- [Reasoning Paths as Signals: Augmenting Multi-hop Fact Verification through Structural Reasoning Progression](https://mlsanity.com/paper/2506.07075/) (2025)

## Abstract (arXiv)

Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches follow a three-step pipeline framework, including document retrieval, sentence retrieval and claim verification. High-quality evidences provided by the first two steps are the foundation of the effective reasoning in the last step. Despite being important, high-quality evidences are rarely studied by existing works for FV, which often adopt the off-the-shelf models to retrieve relevant documents and sentences in an "index-retrieve-then-rank" fashion. This classical approach has clear drawbacks as follows: i) a large document index as well as a complicated search process is required, leading to considerable memory and computational overhead; ii) independent scoring paradigms fail to capture the interactions among documents and sentences in ranking; iii) a fixed number of sentences are selected to form the final evidence set. In this work, we propose GERE, the first system that retrieves evidences in a generative fashion, i.e., generating the document titles as well as evidence sentence identifiers. This enables us to mitigate the aforementioned technical issues since: i) the memory and computational cost is greatly reduced because the document index is eliminated and the heavy ranking process is replaced by a light generative process; ii) the dependency between documents and that between sentences could be captured via sequential generation process; iii) the generative formulation allows us to dynamically select a precise set of relevant evidences for each claim. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines, with both time-efficiency and memory-efficiency.