Rhitabrat Pokharel
pokharel [at] pdx.edu.

I am a PhD Candidate in Computer Science (Natural Language Processing) at Portland State University, under the guidance of Dr. Ameeta Agrawal (PortNLP Lab). Currently, I am working on improving LLM’s multilingual ability. I have also worked on projected related to low-resource languages, machine translation (MT), MT post-editing (MTPE), idiomaticity, multi-word expressions, and social media information extraction.
I am on the lookout for Internship or Full-Time positions.

Latest News
Feb, 2025 | 🏆 Got accepted to the NAIRR Pilot AI Unlocked Workshop (NSF funded) in Denver this April! |
---|---|
Jan, 2025 | ✍🏼 Got a paper on model scaling accepted at SEAS workshop (AAAI 2025). |
Jan, 2025 | 🎤 Presented a paper at CHiPSAL workshop (COLING 2025). |
Nov, 2024 | 🎯 Successfully defended my PhD proposal titled Enhanced Multilingual Text Generation with Large Language Models. |
Nov, 2024 | 🌱 Co-mentored Paola during her NSF REU internship at PSU. |
Publications
- The Impact of Model Scaling on Seen and Unseen Language PerformanceIn Scalable and Efficient Artificial Intelligence Systems, 2025
- neDIOM: Dataset and Analysis of Nepali IdiomsIn Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025), 2025
- Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language ModelsIn Proceedings of the First Workshop on Language Models for Low-Resource Languages, 2025
- Multilingual Evaluation of Long Context Retrieval and ReasoningIn Proceedings of the 4th Workshop on Multi-lingual Representation Learning (MRL), 2024
- Generating Continuations in Multilingual Idiomatic ContextsIn Proceedings of the 3rd Workshop on Multi-lingual Representation Learning (MRL), 2023
- All Translation Tools Are Not Equal: Investigating the Quality of Language Translation for Forced MigrationIn 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA), 2023
- Estimating Semantic Similarity between In-Domain and Out-of-Domain SamplesIn Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), 2023
- Machine Learning Predictions of Electricity CapacityEnergies, 2023
- Classifying YouTube Comments Based on Sentiment and Type of SentencearXiv preprint arXiv:2111.01908, 2021
Seminars and Talks
[Conference Poster Presentation] -- nediom: Dataset and Analysis of Nepali Idioms, CHiPSAL [COLING], 2025. [Virtual][Conference Poster Presentation] -- Generating Continuations in Multilingual Idiomatic Contexts, MRL [EMNLP], 2023. [Virtual]
[Conference Presentation] -- Estimating Semantic Similarity between In-Domain and Out-of-Domain Samples, *SEM [ACL], 2023. [In Person]
[Conference Poster Presentation] -- Estimating Semantic Similarity between In-Domain and Out-of-Domain Samples, *SEM [ACL], 2023. [In Person]
Professional Services
[Reviewer] -- COLING, Computational Intelligence, Undergraduate Students Scholarship at Portland State University.[Sub-reviewer] -- ACL, EMNLP, NAACL, ARR.
[Co-Founder] -- MRFOSS Club (a club for open source software initiatives) -- 2018.