arXiv subjects

Ghazal Kalhor

Publications and source records attributed to Ghazal Kalhor.

11 recordsLinked to original sources

arXiv2026

PERCEPT: A Corpus for POS Tagging and Analysis of Persian-English Code-Mixing

Social media has become a major venue for multilingual communication, where users frequently mix multiple languages within a single utterance. Although code-mixed corpora have been developed for several language pairs, Persian-English code-mixing remains relatively underexplored. Existing Persian resources lack Universal Dependencies (UD) part-of-speech (POS) annotations for code-mixed words, limiting both linguistic analyses and the development of syntax-aware NLP models. To address this gap, we introduce PERCEPT, the first publicly available large-scale Persian-English code-mixed corpus annotated with Universal Dependencies POS tags for code-mixed words. The dataset comprises 6,800 posts collected from X, Instagram, and Digikala. We further present an LLM-assisted annotation framework that automatically assigns POS tags and document-level topics. Human evaluation demonstrates high agreement between the automatically generated annotations and gold annotations, confirming the reliability of the annotations. Using PERCEPT, we conduct the first comprehensive linguistic analysis of Persian-English code-mixing across multiple social media platforms. Our analyses reveal that nouns are the predominant category for code-mixed words, while the distributions of other POS categories vary across platforms. We further find that the positional distribution of code-mixed words is remarkably consistent across platforms, whereas the triggering effect is substantially more pronounced in Digikala. PERCEPT is publicly available at https://github.com/kalhorghazal/PERCEPT.

cs.CL↗

arXiv2026

Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)

This report summarizes the CHIIR 2026 Workshop on Generative AI and Academic Search (GAI\&AS), which examined how GenAI is reshaping academic search systems and research practices. The workshop brought together researchers in human information interaction and information retrieval to explore key challenges and opportunities in designing and evaluating future academic search systems that integrate GenAI, moving beyond traditional document retrieval to support summarization, recommendation, synthesis, and conversational interaction. Participants' interests and discussions focused on three thematic clusters: foundations and principles, applications and opportunities, and search-as-learning. Across these themes, the workshop highlighted the importance of academic search systems in supporting transparency, credibility, research integrity, and long-term scholarly needs, as well as in fostering higher-order cognitive processes. Participants discussed guiding theories, design principles, methodological approaches, partnerships, and community-building efforts aimed at advancing human-centered GenAI-enhanced academic search systems. Overall, the workshop demonstrated strong community interest and a diverse range of ongoing and emerging research initiatives at the intersection of GenAI and academic search.

cs.IR↗

arXiv2026

GhazalBench: Canonical Verse Access in LLMs across Persian Ghazals and Shakespearean Sonnets

Persian poetry plays an active role in Iranian cultural practice, where verses by canonical poets such as Hafez and Saadi are frequently quoted, paraphrased, or completed from incomplete cues. Supporting such interactions requires language models to reliably access canonical verses from semantic and lexical information. We introduce GhazalBench, a benchmark for evaluating how large language models (LLMs) access the canonical surface forms of Persian ghazal under usage-grounded conditions. Unlike prior work that primarily treats memorization as a liability, GhazalBench studies settings in which access to exact wording is functionally important. The benchmark evaluates completion and recognition under varied semantic and lexical cues. Across proprietary and open-weight multilingual LLMs, exact completion remains challenging, while recognition is substantially stronger. Performance also varies across poets and model families. Parallel experiments on Shakespearean sonnets yield markedly higher completion for several models, consistent with differences in exposure to canonical texts. {Additional experiments suggest that post-training may reduce direct continuation-based access to canonical text.} Our findings motivate evaluation frameworks that distinguish production from recognition and assess access to culturally significant canonical texts. GhazalBench is available at https://github.com/kalhorghazal/GhazalBench.

cs.CL↗

arXiv2026

MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs

In recent years, multilingual Large Language Models (LLMs) have become an inseparable part of daily life, making it crucial for them to master the rules of conversational language in order to communicate effectively with users. While previous work has evaluated LLMs' understanding of figurative language in high-resource languages, their performance in low-resource languages remains underexplored. In this paper, we introduce MasalBench, a comprehensive benchmark for assessing LLMs' contextual and cross-cultural understanding of Persian proverbs, which are a key component of conversation in this low-resource language. We evaluate eight state-of-the-art LLMs on MasalBench and find that they perform well in identifying Persian proverbs in context, achieving accuracies above 0.90. However, their performance drops considerably when tasked with identifying equivalent English proverbs, with the best model achieving 0.79 accuracy. Our findings highlight the limitations of current LLMs in cultural knowledge and analogical reasoning, and they provide a framework for assessing cross-cultural understanding in other low-resource languages. MasalBench is available at https://github.com/kalhorghazal/MasalBench.

cs.CL↗

arXiv2025

Remembering Unequally: Global and Disciplinary Bias in LLM Reconstruction of Scholarly Coauthor Lists

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.

cs.CL↗

arXiv2025

Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persian

Multilingual Large Language Models (LLMs) are increasingly used worldwide, making it essential to ensure they are free from gender bias to prevent representational harm. While prior studies have examined such biases in high-resource languages, low-resource languages remain understudied. In this paper, we propose a template-based probing methodology, validated against real-world data, to uncover gender stereotypes in LLMs. As part of this framework, we introduce the Domain-Specific Gender Skew Index (DS-GSI), a metric that quantifies deviations from gender parity. We evaluate four prominent models, GPT-4o mini, DeepSeek R1, Gemini 2.0 Flash, and Qwen QwQ 32B, across four semantic domains, focusing on Persian, a low-resource language with distinct linguistic features. Our results show that all models exhibit gender stereotypes, with greater disparities in Persian than in English across all domains. Among these, sports reflect the most rigid gender biases. This study underscores the need for inclusive NLP practices and provides a framework for assessing bias in other low-resource languages.

cs.CL↗

arXiv2024

Forecasting Success of Computer Science Professors and Students Based on Their Academic and Personal Backgrounds

After completing their undergraduate studies, many computer science (CS) students apply for competitive graduate programs in North America. Their long-term goal is often to be hired by one of the big five tech companies or to become a faculty member. Therefore, being aware of the role of admission criteria may help them choose the best path towards their goals. In this paper, we analyze the influence of students' previous universities on their chances of being accepted to prestigious North American universities and returning to academia as professors in the future. Our findings demonstrate that the ranking of their prior universities is a significant factor in achieving their goals. We then illustrate that there is a bias in the undergraduate institutions of students admitted to the top 25 computer science programs. Finally, we employ machine learning models to forecast the success of professors at these universities. We achieved an RMSE of 7.85 for this prediction task.

cs.CY↗

arXiv2024

Understanding Trends, Patterns, and Dynamics in Global Company Acquisitions: A Network Perspective

Studying acquisitions offers invaluable insights into startup trends, aiding informed investment decisions for businesses. However, the scarcity of studies in this domain prompts our focus on shedding light in this area. Employing Crunchbase data, our study delves into the global network of company acquisitions using diverse network analysis techniques. Our findings unveil an acquisition network characterized by a primarily sparse structure comprising localized dense connections. We reveal a prevalent tendency among organizations to acquire companies within their own country and industry, as well as those within the same age bracket. Furthermore, we show that the country, region, city, and category of the companies can affect the formation of acquisition relationships between them. Our temporal analysis indicates a growth in the number of weakly connected components of the network over time, accompanied by a trend toward a sparser network. Through centrality metrics computation in the cross-city acquisition network, we identify New York, London, and San Francisco as pivotal and central hubs in the global economic landscape. Finally, we show that the United States, United Kingdom, and Germany are predominant countries in international acquisitions. The insights from our research assist policymakers in crafting better regulations to foster global economic growth, and aid businesses in deciding which startups to acquire and which markets to target for expansion.

cs.SI↗

arXiv2023

Analysis of Research Trends in Computer Science: A Network Approach

Nowadays, computer science (CS) has emerged as a dominant force in numerous research areas both within and beyond its own discipline. However, despite its significant impact on scholarly space, only a limited number of studies have been conducted to analyze the research trends and relationships within computer science. In this study, we collected information on fields and subfields from over 2,000 research articles published in the 2022 proceedings of the top Association for Computing Machinery (ACM) conferences spanning various research fields. Through a network approach, we investigated the interconnections between CS fields and subfields to evaluate their interdisciplinarity and multidisciplinarity. Our findings indicate that computing methodologies and privacy and security stand out as the most interdisciplinary fields, while human-centered computing exhibits the highest frequency among the papers. Furthermore, we discovered that machine learning emerges as the most interdisciplinary and multidisciplinary subfield within computer science. These results offer valuable insights for universities seeking to foster interdisciplinary research opportunities for their students.

cs.SI↗

arXiv2023

Diversity dilemmas: uncovering gender and nationality biases in graduate admissions across top North American computer science programs

Although different organizations have defined policies towards diversity in academia, many argue that minorities are still disadvantaged in university admissions due to biases. Extensive research has been conducted on detecting partiality patterns in the academic community. However, in the last few decades, limited research has focused on assessing gender and nationality biases in graduate admission results of universities. In this study, we collected a novel and comprehensive dataset containing information on approximately 14,000 graduate students majoring in computer science (CS) at the top 25 North American universities. We used statistical hypothesis tests to determine whether there is a preference for students' gender and nationality in the admission processes. In addition to partiality patterns, we discuss the relationship between gender/nationality diversity and the scientific achievements of research teams. Consistent with previous studies, our findings show that there is no gender bias in the admission of graduate students to research groups, but we observed bias based on students' nationality.

cs.CY↗

arXiv2023

Gender Gaps in Online Social Connectivity, Promotion and Relocation Reports on LinkedIn

Online professional social networking platforms provide opportunities to expand networks strategically for job opportunities and career advancement. A large body of research shows that women's offline networks are less advantageous than men's. How online platforms such as LinkedIn may reflect or reproduce gendered networking behaviours, or how online social connectivity may affect outcomes differentially by gender is not well understood. This paper analyses aggregate, anonymised data from almost 10 million LinkedIn users in the UK and US information technology (IT) sector collected from the site's advertising platform to explore how being connected to Big Tech companies ('social connectivity') varies by gender, and how gender, age, seniority and social connectivity shape the propensity to report job promotions or relocations. Consistent with previous studies, we find there are fewer women compared to men on LinkedIn in IT. Furthermore, female users are less likely to be connected to Big Tech companies than men. However, when we further analyse recent promotion or relocation reports, we find women are more likely than men to have reported a recent promotion at work, suggesting high-achieving women may be self-selecting onto LinkedIn. Even among this positively selected group, though, we find men are more likely to report a recent relocation. Social connectivity emerges as a significant predictor of promotion and relocation reports, with an interaction effect between gender and social connectivity indicating the payoffs to social connectivity for promotion and relocation reports are larger for women. This suggests that online networking has the potential for larger impacts for women, who experience greater disadvantage in traditional networking contexts, and calls for further research to understand differential impacts of online networking for socially disadvantaged groups.

cs.SI↗