cv

Research Associate

Cohere for AI

Research on data selection and clustering for instruction fine-tuning.

• Collaborating with Liangyu Chen, Marzieh Fadaee, Sara Ahmadian

Machine Learning Engineer Intern

Expedia Group, Inc.

Worked on deploying AI models more efficiently for business applications in the Expedia For Business (E4B) teams.

• Designed and assisted in the deployment of Machine Learning models through a streamlined pipeline using ONNX and CI/CD tools
• Migrated deployment pipeline from Jenkins to GitHub Actions
• Employed CI/CD tools (Spinnaker, Github Actions) and Cloud Services (AWS S3 Bucket, Lambda)

Research Assistant

Institute for Language, Cognition and Computation (ILCC), University of Edinburgh

Research in Supervised Contrastive Learning in NLP, Few-shot learning, Commonsense Question Answering.

• 1 Paper Accepted by ACL 2023 Main (Poster)
• Supervised by Dr Jeff Z. Pan

Research Intern

Huawei Noah's Lab R&D

Specialized in E-commerce Knowledge Graphs, Entity Linking, and Disambiguation from unstructured data.

• Enhanced the performance of the entity extraction module
• Contributed to benchmarking work
• Assisted in the design and development of the product's Knowledge Graph
• Leveraged data processing tools such as Apache Spark and Hadoop
• Employed CI/CD tools (Nexus Repository, Jenkins)

PhD

Northeastern University

Conversational Agent, Alignment, Safety in ML

MSc. (by Research)

The University of Edinburgh

Safety in NLP, Instruction Tuning

BSc

The University of Edinburgh

Artificial Intelligence and Computer Science

• Natural Language Understanding
• Generation, and Machine Translation
• Text Technologies for Data Science
• Software Engineering and Professional Practice

Outstanding Dissertation Award

The University of Edinburgh

Scored top (90%) in the final year dissertation among the class

Evaluating the Adversarial Robustness of Retrieval-Based In-Context Learning for Large Language Models

Conference on Language Modeling 2024 (COLM-2024)

Co-authored with Jie He, Pasquale Miniverini, and Jeff Pan

Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?

Under review

Co-authored with Pinzhen Chen, Zhicheng Guo, Barry Haddow

Fine-Tuning Large Language Models with Sequential Instructions

Under review

Co-authored with Hanxu Hu and Pinzhen Chen

BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering

The 2023 Annual Meeting of the Association for Computational Linguistics (Main, ACL-2023)

Co-authored with Jie He, Victor Gutierrez-Basulto, and Jeff Pan

Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification

The 2023 Conference on Empirical Methods in Natural Language Processing (Findings, EMNLP-2023)

Co-authored with Jie He, Victor Gutierrez-Basulto, and Jeff Pan