{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/aic-ctu-system-at-averitec-re-framing","title":"AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task","arxiv_id":"2410.11446","date":"2024-10-15","proceeding":null,"authors":["Herbert Ullrich","Tomáš Mlynář","Jan Drchal"],"abstract":"This paper describes our $3^{rd}$ 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.","url_abs":"https://arxiv.org/abs/2410.11446v1","url_pdf":"https://arxiv.org/pdf/2410.11446v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"aic-ctu-system-at-averitec-re-framing","repo_url":"https://github.com/aic-factcheck/aic_averitec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fact-checking-on-averitec","task":"Fact Checking","dataset":"AVeriTeC","model":"CTU AIC","rank_in_archive_order":2,"of":3,"metrics":{"AveriTeC":"0.5","Question + Answer score":"0.32","Question Only score":"0.46"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}