Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking

Dina Pisarevskaya, Arkaitz Zubiaga
1/18/2025
cs.CLcs.AI

No official code found. Best implementation: deenochka/ClaimMatch_dataset (0 stars, last commit 2025-02-28).

Abstract

The claim matching (CM) task can benefit an automated fact-checking pipeline by putting together claims that can be resolved with the same fact-check. In this work, we are the first to explore zero-shot and few-shot learning approaches to the task. We consider CM as a binary classification task and experiment with a set of instruction-following large language models (GPT-3.5-turbo, Gemini-1.5-flash, Mistral-7B-Instruct, and Llama-3-8B-Instruct), investigating prompt templates. We introduce a new CM dataset, ClaimMatch, which will be released upon acceptance. We put LLMs to the test in the CM task and find that it can be tackled by leveraging more mature yet similar tasks such as natural language inference or paraphrase detection. We also propose a pipeline for CM, which we evaluate on texts of different lengths.

View on arXivView PDF

Code Implementations(1)

deenochka/ClaimMatch_datasetCommunity64%

The dataset for the paper "Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking"

00Feb 28, 20251 years ago

Similar Papers

FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs

86% match2 repos72.8k2024

Agent-based Automated Claim Matching with Instruction-following LLMs

84% match2025

One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking

84% match2026

Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs

84% match1 repo72024

Zero-Shot Learning and Key Points Are All You Need for Automated Fact-Checking

83% match2024

Are LLMs Good Zero-Shot Fallacy Classifiers?

82% match1 repo52024

Cite this paper

@article{pisarevskaya2025zeroshot,
  title  = {Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking},
  author = {Dina Pisarevskaya and Arkaitz Zubiaga},
  year   = {2025},
  eprint = {2501.10860},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.10860v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.10860.svg)](https://codeofpaper.com/paper/2501.10860)

Discussion