Publications

Multilingual Routing in Mixture-of-Experts

Lucas Bandarkar, Chenyuan Yang, Mohsen Fayyaz, Junlin Hu, Nanyun Peng

UCLA

preprinted Oct 2025

ArXiV / Semantic Scholar

The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs

Lucas Bandarkar, Nanyun Peng

UCLA

MRL Workshop at EMNLP 2025 (Nov 2025, preprinted May 2025)

ACL Anthology / ArXiV / Semantic Scholar

Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models

Lucas Bandarkar, Benjamin Muller, Pritish Yuvraj, Rui Hou, Nayan Singhal, Hongjiang Lv, Bing Liu

Meta GenAI

ICLR 2025, Spotlight Paper (Apr 2025, preprinted Oct 2024)

OpenReview / ArXiV / Semantic Scholar

The BELEBELE Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants

Lucas Bandarkar, Davis Liang, Benjamin Muller, Mikel Artetxe, Satya Narayan Shukla, Donald Husa, Naman Goyal, Abhinandan Krishnan, Luke Zettlemoyer, Madian Khabsa

Meta AI

ACL 2024 (Aug 2024, preprinted Aug 2023)

ACL Anthology / Meta Research Page / Website & Download / HuggingFace / Semantic Scholar

SNaRe: Domain-aware Data Generation for Low-Resource Event Detection

Tanmay Parekh, Yuxuan Dong, Lucas Bandarkar, Artin Kim, I-Hung Hsu, Kai-Wei Chang, Nanyun Peng

UCLA

EMNLP 2025 (Nov 2025, preprinted Feb 2025)

ArXiv / Code / Semantic Scholar

Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test

Philippe Laban, Luke Dai, Lucas Bandarkar, Marti Hearst

UC Berkeley

ACL 2021 (Jul 2021)

ACL Anthology / ArXiV / Code / Semantic Scholar

News Headline Grouping as a Challenging NLU Task

Philippe Laban, Lucas Bandarkar, Marti Hearst

UC Berkeley

NAACL 2021 (May 2021)

ACL Anthology / ArXiV / Code / HuggingFace / Semantic Scholar

IndiaWeatherBench: A Dataset and Benchmark for Data-Driven Regional Weather Forecasting over India

Tung Nguyen, Harkanwar Singh, Nilay Naharas, Lucas Bandarkar, Aditya Grover

UCLA

preprinted Aug 2025

ArXiV / Code / Semantic Scholar