PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation

Albert Gong, Kamilė Stankevičiūtė, Chao Wan, Anmol Kabra, Raphael Thesmar, Johann Lee, Julius Klenke, Carla P Gomes, Kilian Q Weinberger

Keywords: logical reasoning, information retrieval, data memorization, data leakage, LLM evaluation, retrieval-augmented generation, agentic workflows, LLM agents, multi-hop reasoning, data contamination, large language models

Abstract: High-quality benchmarks are essential for evaluating reasoning and retrieval capabilities of large language models (LLMs). However, curating datasets for this purpose is not a permanent solution as they are prone to data leakage and inflated performance results. To address these challenges, we propose PhantomWiki: a pipeline to generate unique, factually consistent document corpora with diverse question-answer pairs. Unlike prior work, PhantomWiki is neither a fixed dataset, nor is it based on any existing data. Instead, a new PhantomWiki instance is generated on demand for each evaluation. We vary the question difficulty and corpus size to disentangle reasoning and retrieval capabilities, respectively, and find that PhantomWiki datasets are surprisingly challenging for frontier LLMs. Thus, we contribute a scalable and data leakage-resistant framework for disentangled evaluation of reasoning, retrieval, and tool-use abilities.

Submission Number: 65