# SourceBench: Can AI Answers Reference Quality Web Sources?

arXiv: https://arxiv.org/abs/2602.16942 · HTML: https://mlsanity.com/paper/2602.16942/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [Citations and Trust in LLM Generated Responses](https://mlsanity.com/paper/2501.01303/) (2025)
- [DebateQA: Evaluating Question Answering on Debatable Knowledge](https://mlsanity.com/paper/2408.01419/) (2024)
- [FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning](https://mlsanity.com/paper/2410.06304/) (2024)
- [RAGProbe: An Automated Approach for Evaluating RAG Applications](https://mlsanity.com/paper/2409.19019/) (2024)
- [Dataset of Natural Language Queries for E-Commerce](https://mlsanity.com/paper/2302.06355/) (2023)
- [LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest](https://mlsanity.com/paper/2509.03764/) (2025)
- [TRUE: A Reproducible Framework for LLM-Driven Relevance Judgment in Information Retrieval](https://mlsanity.com/paper/2509.25602/) (2025)

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

- [Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs](https://mlsanity.com/paper/2605.28565/) (2026)

## Abstract (arXiv)

Large language models (LLMs) increasingly answer queries by citing web sources, but existing evaluations emphasize answer correctness rather than evidence quality. We introduce SourceBench, a benchmark for measuring the quality of cited web sources across 100 real-world queries spanning informational, factual, argumentative, social, and shopping intents. SourceBench uses an eight-metric framework covering content quality (content relevance, factual accuracy, objectivity) and page-level signals (e.g., freshness, authority/accountability, clarity), and includes a human-labeled dataset with a calibrated LLM-based evaluator that matches expert judgments closely. We evaluate eight LLMs, Google Search, and three AI search tools over 3996 cited sources using SourceBench and conduct further experiments to understand the evaluation results. Overall, our work reveals four key new insights that can guide future research in the direction of GenAI and web search.