Dense X Retrieval: What Retrieval Granularity Should We Use? (EMNLP, 2024)
MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity (EMNLP, 2024)
Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness (COLM, 2024)
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts (ACL (Findings), 2024)
Sub-sentence Encoder: Contrastive Learning of Propositional Semantic Representations (NAACL, 2024)
ExpertQA: Expert-Curated Questions and Attributed Answers (NAACL, 2024)
The Trickle-down Impact of Reward (In-)consistency on RLHF (ICLR, 2024)
Using LLM for Improving Key Event Discovery: Temporal-Guided News Stream Clustering with Event Summaries (EMNLP (Findings), 2023)
PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition (ACL (Findings), 2023)
Stretching Sentence-Pair NLI datasets to Reason Over Long Document And Clusters (EMNLP (Findings), 2022)
Design Challenge for a Multi-Perspective Search Engine (NAACL (Findings), 2022)
Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection (NAACL, 2021)
MULTIOPED: A Corpus of Multi-Perspective News Editorials (NAACL, 2021)
Evaluating Models’ Local Decision Boundaries via Contrast Sets (EMNLP Findings, 2020)
Do VQA Models Know What to Look At? (Women in CV (WiCV) Workshop at ECCV, 2020)
PerspectroScope: A Window to the World of Diverse Perspectives (ACL - Demos, 2019)
Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims (NAACL, 2019)
Research Experience
Senior Applied Scientist at Microsoft Office of Applied Research
Education
Ph.D. - University of Pennsylvania (Advisor: Dan Roth)
Background
A Senior Applied Scientist at Microsoft Office of Applied Research, focusing on applications of language models. Recently received his Ph.D. from the University of Pennsylvania.