# KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking

arXiv: https://arxiv.org/abs/2601.19447 · HTML: https://mlsanity.com/paper/2601.19447/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 65 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 4 of 4)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [A Graph-based Verification Framework for Fact-Checking](https://mlsanity.com/paper/2503.07282/) (2025)
- [Detecting Manipulated Contents Using Knowledge-Grounded Inference](https://mlsanity.com/paper/2504.21165/) (2025)

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

- [Latent Causal Void: Explicit Missing-Context Reconstruction for Misinformation Detection](https://mlsanity.com/paper/2605.12156/) (2026)

## Abstract (arXiv)

Claim verification is a core component of automated fact-checking systems, aimed at determining the truthfulness of a statement by assessing it against reliable evidence sources such as documents or knowledge bases. This work presents KG-CRAFT, a method that improves automatic claim verification by leveraging large language models (LLMs) augmented with contrastive questions grounded in a knowledge graph. KG-CRAFT first constructs a knowledge graph from claims and associated reports, then formulates contextually relevant contrastive questions based on the knowledge graph structure. These questions guide the distillation of evidence-based reports, which are synthesised into a concise summary that is used for veracity assessment by LLMs. Extensive evaluations on two real-world datasets (LIAR-RAW and RAWFC) demonstrate that our method achieves a new state-of-the-art in predictive performance. Comprehensive analyses validate in detail the effectiveness of our knowledge graph-based contrastive reasoning approach in improving LLMs' fact-checking capabilities.