# Claim Check-Worthiness Detection: How Well do LLMs Grasp Annotation Guidelines?

arXiv: https://arxiv.org/abs/2404.12174 · HTML: https://mlsanity.com/paper/2404.12174/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 11 of 11)

- [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)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society](https://mlsanity.com/paper/2005.00033/) (2020)
- [Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection](https://mlsanity.com/paper/1809.08193/) (2018)
- [Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong](https://mlsanity.com/paper/2310.12558/) (2023)
- [Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation](https://mlsanity.com/paper/2210.13865/) (2022)
- [AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators](https://mlsanity.com/paper/2402.11073/) (2024)
- [NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge](https://mlsanity.com/paper/2112.08544/) (2021)

## Built on by (most cited first, 9 of 9)

- [Towards Effective Extraction and Evaluation of Factual Claims](https://mlsanity.com/paper/2502.10855/) (2025)
- [HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims](https://mlsanity.com/paper/2502.11753/) (2025)
- [Assessing the Potential of Generative Agents in Crowdsourced Fact-Checking](https://mlsanity.com/paper/2504.19940/) (2025)
- [Self-Adaptive Paraphrasing and Preference Learning for Improved Claim Verifiability](https://mlsanity.com/paper/2412.11653/) (2024)
- [When Hate Meets Facts: LLMs-in-the-Loop for Check-worthiness Detection in Hate Speech](https://mlsanity.com/paper/2603.25269/) (2026)
- [LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics](https://mlsanity.com/paper/2605.13412/) (2026)
- [Multilingual and Cross-Lingual Citation Needed Detection on Wikipedia for Lower-Resource Languages](https://mlsanity.com/paper/2605.31136/) (2026)
- [Calibrating Small Language Models for Claim Check-Worthiness Detection](https://mlsanity.com/paper/2608.30731/) (2026)
- [VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation](https://mlsanity.com/paper/2609.35028/) (2026)

## Abstract (arXiv)

The increasing threat of disinformation calls for automating parts of the fact-checking pipeline. Identifying text segments requiring fact-checking is known as claim detection (CD) and claim check-worthiness detection (CW), the latter incorporating complex domain-specific criteria of worthiness and often framed as a ranking task. Zero- and few-shot LLM prompting is an attractive option for both tasks, as it bypasses the need for labeled datasets and allows verbalized claim and worthiness criteria to be directly used for prompting. We evaluate the LLMs' predictive and calibration accuracy on five CD/CW datasets from diverse domains, each utilizing a different worthiness criterion. We investigate two key aspects: (1) how best to distill factuality and worthiness criteria into a prompt and (2) what amount of context to provide for each claim. To this end, we experiment with varying the level of prompt verbosity and the amount of contextual information provided to the model. Our results show that optimal prompt verbosity is domain-dependent, adding context does not improve performance, and confidence scores can be directly used to produce reliable check-worthiness rankings.