Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.00838 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912515611426816 |
|---|---|
| author | Strauss, Ilan Yang, Jangho O'Reilly, Tim Rosenblat, Sruly Moure, Isobel |
| author_facet | Strauss, Ilan Yang, Jangho O'Reilly, Tim Rosenblat, Sruly Moure, Isobel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00838 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Attribution Crisis in LLM Search Results Strauss, Ilan Yang, Jangho O'Reilly, Tim Rosenblat, Sruly Moure, Isobel Digital Libraries Artificial Intelligence Computation and Language 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. |
| title | The Attribution Crisis in LLM Search Results |
| topic | Digital Libraries Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2508.00838 |