# The Attribution Crisis in LLM Search Results

arXiv: https://arxiv.org/abs/2508.00838 · HTML: https://mlsanity.com/paper/2508.00838/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Builds on (most cited first, 13 of 13)

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Automatic Evaluation of Attribution by Large Language Models](https://mlsanity.com/paper/2305.06311/) (2023)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges](https://mlsanity.com/paper/2408.08946/) (2024)
- [Source-Aware Training Enables Knowledge Attribution in Language Models](https://mlsanity.com/paper/2404.01019/) (2024)
- [Citation: A Key to Building Responsible and Accountable Large Language Models](https://mlsanity.com/paper/2307.02185/) (2023)
- [Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text](https://mlsanity.com/paper/2501.03212/) (2025)
- [Abstention vs. Hallucination: Benchmarking LLM Source Attribution for Scientific Citations](https://mlsanity.com/paper/2405.02228/) (2024)
- [Beyond Public Access in LLM Pre-Training Data](https://mlsanity.com/paper/2505.00020/) (2025)
- [LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis](https://mlsanity.com/paper/2506.12100/) (2025)

## Built on by (most cited first, 3 of 3)

- [MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution](https://mlsanity.com/paper/2512.05958/) (2025)
- [Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents](https://mlsanity.com/paper/2605.22203/) (2026)
- [The Agentic Web Requires New Normative Infrastructure](https://mlsanity.com/paper/2606.10711/) (2026)

## Abstract (arXiv)

Web-enabled LLMs frequently answer queries without crediting the web pages they consume, creating an "attribution gap" - the difference between relevant URLs read and those actually cited. Drawing on approximately 14,000 real-world LMArena conversation logs with search-enabled LLM systems, we document three exploitation patterns: 1) No Search: 34% of Google Gemini and 24% of OpenAI GPT-4o responses are generated without explicitly fetching any online content; 2) No citation: Gemini provides no clickable citation source in 92% of answers; 3) High-volume, low-credit: Perplexity's Sonar visits approximately 10 relevant pages per query but cites only three to four. A negative binomial hurdle model shows that the average query answered by Gemini or Sonar leaves about 3 relevant websites uncited, whereas GPT-4o's tiny uncited gap is best explained by its selective log disclosures rather than by better attribution. Citation efficiency - extra citations provided per additional relevant web page visited - varies widely across models, from 0.19 to 0.45 on identical queries, underscoring that retrieval design, not technical limits, shapes ecosystem impact. We recommend a transparent LLM search architecture based on standardized telemetry and full disclosure of search traces and citation logs.