mlsanityData to 14 Oct 2026

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

arXiv 2501.10860 ↗First posted 18 Jan 2025cs.CL cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 18 Jan 2025.

Builds on

34 of 50 references.

References · 34

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  10. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  11. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  12. 2019How Can We Know What Language Models Know?cited by 959
22 more
  1. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  2. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  3. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  4. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
  5. 2021True Few-Shot Learning with Language Modelscited by 344
  6. 2021Do Prompt-Based Models Really Understand the Meaning of their Prompts?cited by 326
  7. 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 289
  8. 2021How Many Data Points is a Prompt Worth?cited by 198
  9. 2021Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Modelscited by 139
  10. 2021Entailment as Few-Shot Learnercited by 123
  11. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  12. 2020That is a Known Lie: Detecting Previously Fact-Checked Claimscited by 82
  13. 2021Automated Fact-Checking: A Surveycited by 55
  14. 2020Overview of CheckThat! 2020: Automatic Identification and Verification of Claims in Social Mediacited by 46
  15. 2022How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Modelscited by 44
  16. 2021Claim Matching Beyond English to Scale Global Fact-Checkingcited by 42
  17. 2024FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMscited by 27
  18. 2021Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Documentcited by 19
  19. 2023Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformationcited by 19
  20. 2021The Role of Context in Detecting Previously Fact-Checked Claimscited by 17
  21. 2022Matching Tweets With Applicable Fact-Checks Across Languagescited by 15
  22. 2022BEIKE NLP at SemEval-2022 Task 4: Prompt-Based Paragraph Classification for Patronizing and Condescending Language Detectioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 5.

12 papers.

  1. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Modelscited by 13
  2. 2026VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checkingcited by 6
  3. 2025Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learningcited by 5
  4. 2025ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claimscited by 2
  5. 2025Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approachescited by 1
  6. 2025Instance-level Randomization: Toward More Stable LLM Evaluationscited by 1
  7. 2025Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detectioncited by 1
  8. 2026MultiCaption: Detecting disinformation using multilingual visual claimscited by 1
  9. 2026User-Centric Evidence Ranking for Attribution and Fact Verificationcited by 1
  10. 2025Agent-based Automated Claim Matching with Instruction-following LLMscited by 0
  11. 2026BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checkingcited by 0
  12. 2026ModTGCN: Modularity-aware Graph Neural Networks for Text Classificationcited by 0