Raghav Mantri

Dr. Raghav Mantri


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
FTFrancesco Tinner
Francesco Tinner
RMRaghav Mantri
Raghav Mantri
MHMammad Hajili
Mammad Hajili
CCChiamaka Chukwuneke
Chiamaka Chukwuneke
DMDylan Massey
Dylan Massey
DADuygu Ataman
Duygu Ataman
Francesco Tinner, Raghav Mantri, Mammad Hajili, Chiamaka Chukwuneke, Dylan Massey, Benjamin A. Ajibade, Bilge Deniz Kocak, Abolade Dawud, Jonathan Atala, Hale Sirin, Kayode Olaleye, Anar Rzayev, David Adelani, Duygu Ataman. Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024). 2024.

18 May 2026 in Information
Verified
Journal Article
Open access
PDF file
RMRaghav Mantri
Raghav Mantri
XCXin Chen
Xin Chen
YWYixuan Wang
Yixuan Wang
DADuygu Ataman
Duygu Ataman
As large language models (LLMs) scale to cover more languages, their potential to support low-resource settings becomes increasingly promising. However, the mechanisms underlying cross-lingual transfer and the factors that facilitate it remain insufficiently understood. Prior work has highlighted the role of linguistic similarity—particularly syntactic structure—in enabling transfer across languages. In this study, we present a broad empirical analysis of how multilingual LLMs encode and relate structural information across languages with varying typological properties. We combine multiple complementary methods, including hidden-state similarity analysis, typological correlation, probing for syntactic features, and attention-based structural comparisons, across four multilingual models and thirteen languages. Our findings show consistent correlations between representational similarity and syntactic relatedness, suggesting that structural properties of language influence how information is organized and shared across languages. We further observe that attention-derived structures exhibit partial alignment with gold-standard syntax, though this alignment should be interpreted as heuristic rather than direct evidence of syntactic encoding. Overall, our results provide a comparative empirical perspective on cross-lingual structural bias in multilingual LLMs and highlight the importance of careful methodological interpretation when linking representation geometry to linguistic structure.