From Chaos to Clarity: Claim Normalization to Empower Fact-Checking

TL;DR

This paper introduces ClaimNorm, a task for simplifying social media claims, and proposes CACN, a novel model leveraging reasoning and large language models to improve claim normalization, validated on a new dataset with superior performance.

Contribution

The paper presents ClaimNorm as a new task and introduces CACN, a novel approach utilizing chain-of-thought reasoning and large language models for claim normalization.

Findings

CACN outperforms baseline models in claim normalization tasks.

The CLAN dataset contains over 6,000 social media posts with normalized claims.

Error analysis highlights CACN's strengths and limitations.

Abstract

With the rise of social media, users are exposed to many misleading claims. However, the pervasive noise inherent in these posts presents a challenge in identifying precise and prominent claims that require verification. Extracting the important claims from such posts is arduous and time-consuming, yet it is an underexplored problem. Here, we aim to bridge this gap. We introduce a novel task, Claim Normalization (aka ClaimNorm), which aims to decompose complex and noisy social media posts into more straightforward and understandable forms, termed normalized claims. We propose CACN, a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation, mimicking human reasoning processes, to comprehend intricate claims. Moreover, we capitalize on the in-context learning capabilities of large language models to provide guidance and to improve claim normalization. To evaluate the effectiveness of our proposed model, we meticulously compile a comprehensive real-world dataset, CLAN, comprising more than 6k instances of social media posts alongside their respective normalized claims. Our experiments demonstrate that CACN outperforms several baselines across various evaluation measures. Finally, our rigorous error analysis validates CACN's capabilities and pitfalls.