mlsanityData to 7 Oct 2026

AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task

arXiv 2410.11446 ↗First posted 15 Oct 2024cs.CLcited by 8

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

This paper describes our 3rd place submission in the AVeriTeC shared task in which we attempted to address the challenge of fact-checking with evidence retrieved in the wild using a simple scheme of Retrieval-Augmented Generation (RAG) designed for the task, leveraging the predictive power of Large Language Models. We release our codebase and explain its two modules - the Retriever and the Evidence & Label generator - in detail, justifying their features such as MMR-reranking and Likert-scale confidence estimation. We evaluate our solution on AVeriTeC dev and test set and interpret the results, picking the GPT-4o as the most appropriate model for our pipeline at the time of our publication, with Llama 3.1 70B being a promising open-source alternative. We perform an empirical error analysis to see that faults in our predictions often coincide with noise in the data or ambiguous fact-checks, provoking further research and data augmentation.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 40 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

16 of 40 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2017Billion-scale similarity search with GPUscited by 2,477
  7. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  8. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  9. 2022Teaching language models to support answers with verified quotescited by 290
  10. 2023AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Webcited by 144
  11. 2018The Fact Extraction and VERification (FEVER) Shared Taskcited by 108
  12. 2024A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADEcited by 18
4 more
  1. 2023Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?cited by 16
  2. 2022CsFEVER and CTKFacts: Acquiring Czech data for fact verificationcited by 6
  3. 2023Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Languagecited by 4
  4. 2024On Context-aware Detection of Cherry-picking in News Reportingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2024The Automated Verification of Textual Claims (AVeriTeC) Shared Taskcited by 29
  2. 2025The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Paperscited by 6
  3. 2025Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agentscited by 6
  4. 2025AIC CTU@FEVER 8: On-premise fact checking through long context RAGcited by 3
  5. 2025Fact-checking AI-generated news reports: Can LLMs catch their own lies?cited by 2
  6. 2026AIC CTU@AVerImaTeC: dual-retriever RAG for image-text fact checkingcited by 0
  7. 2026Latent Fact-Checking: Detecting Misinformation through Activation Engineeringcited by 0
  8. 2026Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking
  2. 2025Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification
  3. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs
  4. 2024Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output
  5. 2024Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs
  6. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
  7. 2026Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
  8. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation