Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.00476 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913063587807232 |
|---|---|
| author | Kalhor, Ghazal Mashhadi, Afra |
| author_facet | Kalhor, Ghazal Mashhadi, Afra |
| contents | Ongoing breakthroughs in large language models (LLMs) are reshaping scholarly search and discovery interfaces. While these systems offer new possibilities for navigating scientific knowledge, they also raise concerns about fairness and representational bias rooted in the models' memorized training data. As LLMs are increasingly used to answer queries about researchers and research communities, their ability to accurately reconstruct scholarly coauthor lists becomes an important but underexamined issue. In this study, we investigate how memorization in LLMs affects the reconstruction of coauthor lists and whether this process reflects existing inequalities across academic disciplines and world regions. We evaluate three prominent models, DeepSeek R1, Llama 4 Scout, and Mixtral 8x7B, by comparing their generated coauthor lists against bibliographic reference data. Our analysis reveals a systematic advantage for highly cited researchers, indicating that LLM memorization disproportionately favors already visible scholars. However, this pattern is not uniform: certain disciplines, such as Clinical Medicine, and some regions, including parts of Africa, exhibit more balanced reconstruction outcomes. These findings highlight both the risks and limitations of relying on LLM-generated relational knowledge in scholarly discovery contexts and emphasize the need for careful auditing of memorization-driven biases in LLM-based systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00476 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Remembering Unequally: Global and Disciplinary Bias in LLM Reconstruction of Scholarly Coauthor Lists Kalhor, Ghazal Mashhadi, Afra Computation and Language Ongoing breakthroughs in large language models (LLMs) are reshaping scholarly search and discovery interfaces. While these systems offer new possibilities for navigating scientific knowledge, they also raise concerns about fairness and representational bias rooted in the models' memorized training data. As LLMs are increasingly used to answer queries about researchers and research communities, their ability to accurately reconstruct scholarly coauthor lists becomes an important but underexamined issue. In this study, we investigate how memorization in LLMs affects the reconstruction of coauthor lists and whether this process reflects existing inequalities across academic disciplines and world regions. We evaluate three prominent models, DeepSeek R1, Llama 4 Scout, and Mixtral 8x7B, by comparing their generated coauthor lists against bibliographic reference data. Our analysis reveals a systematic advantage for highly cited researchers, indicating that LLM memorization disproportionately favors already visible scholars. However, this pattern is not uniform: certain disciplines, such as Clinical Medicine, and some regions, including parts of Africa, exhibit more balanced reconstruction outcomes. These findings highlight both the risks and limitations of relying on LLM-generated relational knowledge in scholarly discovery contexts and emphasize the need for careful auditing of memorization-driven biases in LLM-based systems. |
| title | Remembering Unequally: Global and Disciplinary Bias in LLM Reconstruction of Scholarly Coauthor Lists |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.00476 |