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

arXiv: https://arxiv.org/abs/2410.11446 · HTML: https://mlsanity.com/paper/2410.11446/

## Key facts

- Cited by 8 papers in the map (data through 14 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.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE](https://mlsanity.com/paper/2403.10407/) (2024)
- [Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?](https://mlsanity.com/paper/2309.08963/) (2023)
- [CsFEVER and CTKFacts: Acquiring Czech data for fact verification](https://mlsanity.com/paper/2201.11115/) (2022)
- [Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language](https://mlsanity.com/paper/2312.10171/) (2023)
- [On Context-aware Detection of Cherry-picking in News Reporting](https://mlsanity.com/paper/2401.05650/) (2024)

## Built on by (most cited first, 8 of 8)

- [The Automated Verification of Textual Claims (AVeriTeC) Shared Task](https://mlsanity.com/paper/2410.23850/) (2024)
- [The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers](https://mlsanity.com/paper/2506.20844/) (2025)
- [Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents](https://mlsanity.com/paper/2507.19090/) (2025)
- [AIC CTU@FEVER 8: On-premise fact checking through long context RAG](https://mlsanity.com/paper/2508.04390/) (2025)
- [Fact-checking AI-generated news reports: Can LLMs catch their own lies?](https://mlsanity.com/paper/2503.18293/) (2025)
- [AIC CTU@AVerImaTeC: dual-retriever RAG for image-text fact checking](https://mlsanity.com/paper/2602.15190/) (2026)
- [Latent Fact-Checking: Detecting Misinformation through Activation Engineering](https://mlsanity.com/paper/2608.06417/) (2026)
- [Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation](https://mlsanity.com/paper/2609.08943/) (2026)

## 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.