This paper describes our system designed forSemEval-2026 Task 10: PsyCoMark—Subtask2: Conspiracy Detection. We proposed a two-stage approach that leverages large-scale pre-trained models and a fine-tuned smaller modelto detect conspiracy theories in text. In thefirst stage, we utilize a large model to test allthe test samples and filter out those that areclearly unrelated to conspiracy theories. Forthe remaining samples, we apply a retrieval-enhanced custom prompt strategy combinedwith the Roberta-Large model in the secondstage. This allows us to fine-tune the modelwith weighted predictions based on relevantretrieved information, enhancing detection ac-curacy. Our system achieved first place onthe leaderboard, with an impressive F1 Scoreof 0.8874. We also present a brief analysisof the effectiveness of the methods used, in-cluding the advantages and limitations of largemodel-based filtering and retrieval-augmentedfine-tuning.

Large language models (LLMs) are increasingly used to automate data analysis through executable code generation. Yet, data science tasks often admit multiple statistically valid solutions—for example, different modeling strategies—making it critical to understand the reasoning behind analyses, not just their outcomes. While manual review of LLM-generated code can help ensure statistical soundness, it is labor-intensive and requires expertise. A more scalable approach is to evaluate the underlying workflows—the logical plans guiding code generation. However, it remains unclear how to assess whether an LLM-generated workflow supports reproducible implementations.To address this, we present **AIRepr**, an **A**nalyst–**I**nspector framework for automatically evaluating and improving the **repr**oducibility of LLM-generated data analysis workflows. Our framework is grounded in statistical principles and supports scalable, automated assessment. We introduce two novel reproducibility-enhancing prompting strategies and benchmark them against standard prompting across 15 analyst–inspector LLM pairs and 1,032 tasks from three public benchmarks. Our findings show that workflows with higher reproducibility also yield more accurate analyses, and that reproducibility-enhancing prompts substantially improve both metrics. This work provides a foundation for transparent, reliable, and efficient human–AI collaboration in data science. Our code is publicly available: [https://github.com/Anonymous-2025-Repr/LLM-DS-Reproducibility](https://github.com/Anonymous-2025-Repr/LLM-DS-Reproducibility)