@inproceedings{sevgili-etal-2024-uhh,
title = "{UHH} at {AV}eri{T}e{C}: {RAG} for Fact-Checking with Real-World Claims",
author = {Sevgili, {\"O}zge and
Nikishina, Irina and
Yimam, Seid Muhie and
Semmann, Martin and
Biemann, Chris},
editor = "Schlichtkrull, Michael and
Chen, Yulong and
Whitehouse, Chenxi and
Deng, Zhenyun and
Akhtar, Mubashara and
Aly, Rami and
Guo, Zhijiang and
Christodoulopoulos, Christos and
Cocarascu, Oana and
Mittal, Arpit and
Thorne, James and
Vlachos, Andreas",
booktitle = "Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.fever-1.5",
pages = "55--63",
abstract = "This paper presents UHH{'}s approach developed for the AVeriTeC shared task. The goal of the challenge is to verify given real-world claims with evidences from the Web. In this shared task, we investigate a Retrieval-Augmented Generation (RAG) model, which mainly contains retrieval, generation, and augmentation components. We start with the selection of the top 10k evidences via BM25 scores, and continue with two approaches to retrieve the most similar evidences: (1) to retrieve top 10 evidences through vector similarity, generate questions for them, and rerank them or (2) to generate questions for the claim and retrieve the most similar evidence, again, through vector similarity. After retrieving the top evidences, a Large Language Model (LLM) is prompted using the claim along with either all evidences or individual evidence to predict the label. Our system submission, $\textbf{UHH}$, using the first approach and individual evidence prompts, ranks 6th out of 23 systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sevgili-etal-2024-uhh">
<titleInfo>
<title>UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claims</title>
</titleInfo>
<name type="personal">
<namePart type="given">Özge</namePart>
<namePart type="family">Sevgili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Nikishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seid</namePart>
<namePart type="given">Muhie</namePart>
<namePart type="family">Yimam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Semmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Schlichtkrull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxi</namePart>
<namePart type="family">Whitehouse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyun</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rami</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijiang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Thorne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents UHH’s approach developed for the AVeriTeC shared task. The goal of the challenge is to verify given real-world claims with evidences from the Web. In this shared task, we investigate a Retrieval-Augmented Generation (RAG) model, which mainly contains retrieval, generation, and augmentation components. We start with the selection of the top 10k evidences via BM25 scores, and continue with two approaches to retrieve the most similar evidences: (1) to retrieve top 10 evidences through vector similarity, generate questions for them, and rerank them or (2) to generate questions for the claim and retrieve the most similar evidence, again, through vector similarity. After retrieving the top evidences, a Large Language Model (LLM) is prompted using the claim along with either all evidences or individual evidence to predict the label. Our system submission, UHH, using the first approach and individual evidence prompts, ranks 6th out of 23 systems.</abstract>
<identifier type="citekey">sevgili-etal-2024-uhh</identifier>
<location>
<url>https://aclanthology.org/2024.fever-1.5</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>55</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claims
%A Sevgili, Özge
%A Nikishina, Irina
%A Yimam, Seid Muhie
%A Semmann, Martin
%A Biemann, Chris
%Y Schlichtkrull, Michael
%Y Chen, Yulong
%Y Whitehouse, Chenxi
%Y Deng, Zhenyun
%Y Akhtar, Mubashara
%Y Aly, Rami
%Y Guo, Zhijiang
%Y Christodoulopoulos, Christos
%Y Cocarascu, Oana
%Y Mittal, Arpit
%Y Thorne, James
%Y Vlachos, Andreas
%S Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F sevgili-etal-2024-uhh
%X This paper presents UHH’s approach developed for the AVeriTeC shared task. The goal of the challenge is to verify given real-world claims with evidences from the Web. In this shared task, we investigate a Retrieval-Augmented Generation (RAG) model, which mainly contains retrieval, generation, and augmentation components. We start with the selection of the top 10k evidences via BM25 scores, and continue with two approaches to retrieve the most similar evidences: (1) to retrieve top 10 evidences through vector similarity, generate questions for them, and rerank them or (2) to generate questions for the claim and retrieve the most similar evidence, again, through vector similarity. After retrieving the top evidences, a Large Language Model (LLM) is prompted using the claim along with either all evidences or individual evidence to predict the label. Our system submission, UHH, using the first approach and individual evidence prompts, ranks 6th out of 23 systems.
%U https://aclanthology.org/2024.fever-1.5
%P 55-63
Markdown (Informal)
[UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claims](https://aclanthology.org/2024.fever-1.5) (Sevgili et al., FEVER 2024)
ACL
- Özge Sevgili, Irina Nikishina, Seid Muhie Yimam, Martin Semmann, and Chris Biemann. 2024. UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claims. In Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER), pages 55–63, Miami, Florida, USA. Association for Computational Linguistics.