Whose Name Comes Up? Auditing LLM-Based Scholar Recommendations

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Barolo, Daniele, Valentin, Chiara, Karimi, Fariba, Galárraga, Luis, Méndez, Gonzalo G., Espín-Noboa, Lisette
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909780044414976
author Barolo, Daniele
Valentin, Chiara
Karimi, Fariba
Galárraga, Luis
Méndez, Gonzalo G.
Espín-Noboa, Lisette
author_facet Barolo, Daniele
Valentin, Chiara
Karimi, Fariba
Galárraga, Luis
Méndez, Gonzalo G.
Espín-Noboa, Lisette
contents This paper evaluates the performance of six open-weight LLMs (llama3-8b, llama3.1-8b, gemma2-9b, mixtral-8x7b, llama3-70b, llama3.1-70b) in recommending experts in physics across five tasks: top-k experts by field, influential scientists by discipline, epoch, seniority, and scholar counterparts. The evaluation examines consistency, factuality, and biases related to gender, ethnicity, academic popularity, and scholar similarity. Using ground-truth data from the American Physical Society and OpenAlex, we establish scholarly benchmarks by comparing model outputs to real-world academic records. Our analysis reveals inconsistencies and biases across all models. mixtral-8x7b produces the most stable outputs, while llama3.1-70b shows the highest variability. Many models exhibit duplication, and some, particularly gemma2-9b and llama3.1-8b, struggle with formatting errors. LLMs generally recommend real scientists, but accuracy drops in field-, epoch-, and seniority-specific queries, consistently favoring senior scholars. Representation biases persist, replicating gender imbalances (reflecting male predominance), under-representing Asian scientists, and over-representing White scholars. Despite some diversity in institutional and collaboration networks, models favor highly cited and productive scholars, reinforcing the rich-getricher effect while offering limited geographical representation. These findings highlight the need to improve LLMs for more reliable and equitable scholarly recommendations.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00074
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Whose Name Comes Up? Auditing LLM-Based Scholar Recommendations
Barolo, Daniele
Valentin, Chiara
Karimi, Fariba
Galárraga, Luis
Méndez, Gonzalo G.
Espín-Noboa, Lisette
Computers and Society
Artificial Intelligence
Digital Libraries
Information Retrieval
Social and Information Networks
Physics and Society
68T50
I.2.7; C.4; F.2; K.4.1
This paper evaluates the performance of six open-weight LLMs (llama3-8b, llama3.1-8b, gemma2-9b, mixtral-8x7b, llama3-70b, llama3.1-70b) in recommending experts in physics across five tasks: top-k experts by field, influential scientists by discipline, epoch, seniority, and scholar counterparts. The evaluation examines consistency, factuality, and biases related to gender, ethnicity, academic popularity, and scholar similarity. Using ground-truth data from the American Physical Society and OpenAlex, we establish scholarly benchmarks by comparing model outputs to real-world academic records. Our analysis reveals inconsistencies and biases across all models. mixtral-8x7b produces the most stable outputs, while llama3.1-70b shows the highest variability. Many models exhibit duplication, and some, particularly gemma2-9b and llama3.1-8b, struggle with formatting errors. LLMs generally recommend real scientists, but accuracy drops in field-, epoch-, and seniority-specific queries, consistently favoring senior scholars. Representation biases persist, replicating gender imbalances (reflecting male predominance), under-representing Asian scientists, and over-representing White scholars. Despite some diversity in institutional and collaboration networks, models favor highly cited and productive scholars, reinforcing the rich-getricher effect while offering limited geographical representation. These findings highlight the need to improve LLMs for more reliable and equitable scholarly recommendations.
title Whose Name Comes Up? Auditing LLM-Based Scholar Recommendations
topic Computers and Society
Artificial Intelligence
Digital Libraries
Information Retrieval
Social and Information Networks
Physics and Society
68T50
I.2.7; C.4; F.2; K.4.1
url https://arxiv.org/abs/2506.00074