# DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification

arXiv: https://arxiv.org/abs/2607.25069 · HTML: https://mlsanity.com/paper/2607.25069/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

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

- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [Overview of CheckThat! 2020: Automatic Identification and Verification of Claims in Social Media](https://mlsanity.com/paper/2007.07997/) (2020)
- [Overview of the CLEF-2018 CheckThat! Lab on Automatic Identification and Verification of Political Claims. Task 1: Check-Worthiness](https://mlsanity.com/paper/1808.05542/) (2018)
- [A Closer Look at Claim Decomposition](https://mlsanity.com/paper/2403.11903/) (2024)
- [QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims](https://mlsanity.com/paper/2403.17169/) (2024)
- [Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document](https://mlsanity.com/paper/2109.07410/) (2021)
- [GR2: Generative Reasoning Re-ranker](https://mlsanity.com/paper/2602.07774/) (2026)
- [DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification](https://mlsanity.com/paper/2507.06195/) (2025)

## Abstract (arXiv)

Automated verification of numerical claims is a challenging problem, as it requires both language understanding and quantitative reasoning. This paper describes our system for CLEF 2026 CheckThat! Task 2, which focuses on ranking reasoning traces generated by large language models (LLMs) and predicting a final verdict for numerical claims in English and Arabic. We explore two approaches. The first approach fine-tunes an LLM-based verifier using LoRA to score each reasoning trace independently as a binary classification problem, and selects the final verdict using Best-of-N selection. We further experiment with adaptive sub-claim decomposition to break complex claims into simpler parts before verification. The second approach uses a lightweight TF-IDF reward model with handcrafted numeric and temporal overlap features to score traces, and aggregates scores by verdict group to determine the final prediction. For Arabic, we compare a general multilingual model against AraBERT, a language-specific model pretrained on Arabic text. Our results show that the LLM-based approach outperforms the lightweight reward model on most metrics, particularly Recall@5, while the reward-based approach shows stronger performance on the Conflicting class. Sub-claim decomposition did not improve performance, suggesting that claim splitting introduces noise rather than aiding reasoning. For Arabic, AraBERT outperforms the multilingual baseline across most metrics.