# Self-Adaptive Paraphrasing and Preference Learning for Improved Claim Verifiability

arXiv: https://arxiv.org/abs/2412.11653 · HTML: https://mlsanity.com/paper/2412.11653/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 10 of 10)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation](https://mlsanity.com/paper/2303.06433/) (2023)
- [NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge](https://mlsanity.com/paper/2112.08544/) (2021)
- [From Chaos to Clarity: Claim Normalization to Empower Fact-Checking](https://mlsanity.com/paper/2310.14338/) (2023)
- [What Makes Medical Claims (Un)Verifiable? Analyzing Entity and Relation Properties for Fact Verification](https://mlsanity.com/paper/2402.01360/) (2024)
- [Claim Check-Worthiness Detection: How Well do LLMs Grasp Annotation Guidelines?](https://mlsanity.com/paper/2404.12174/) (2024)
- [Entity-based Claim Representation Improves Fact-Checking of Medical Content in Tweets](https://mlsanity.com/paper/2209.07834/) (2022)
- [LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback](https://mlsanity.com/paper/2406.03363/) (2024)
- [An Entity-based Claim Extraction Pipeline for Real-world Biomedical Fact-checking](https://mlsanity.com/paper/2304.05268/) (2023)
- [Political claim identification and categorization in a multilingual setting: First experiments](https://mlsanity.com/paper/2310.09256/) (2023)

## Built on by (most cited first, 1 of 1)

- [Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models](https://mlsanity.com/paper/2509.23233/) (2025)

## Abstract (arXiv)

In fact-checking, structure and phrasing of claims critically influence a model's ability to predict verdicts accurately. Social media content in particular rarely serves as optimal input for verification systems, which necessitates pre-processing to extract the claim from noisy context before fact checking. Prior work suggests extracting a claim representation that humans find to be checkworthy and verifiable. This has two limitations: (1) the format may not be optimal for a fact-checking model, and (2), it requires annotated data to learn the extraction task from. We address both issues and propose a method to extract claims that is not reliant on labeled training data. Instead, our self-adaptive approach only requires a black-box fact checking model and a generative language model (LM). Given a tweet, we iteratively optimize the LM to generate a claim paraphrase that increases the performance of a fact checking model. By learning from preference pairs, we align the LM to the fact checker using direct preference optimization. We show that this novel setup extracts a claim paraphrase that is more verifiable than their original social media formulations, and is on par with competitive baselines. For refuted claims, our method consistently outperforms all baselines.