Yuling Gu

RESEARCH

Projects

PhD Student: NYU’s Center for Data Science and NYU Langone Medical Center (September 2025 - present)

• Excited about pushing machine intelligence toward real-world impact, starting a new project soon ...

Predoctoral Young Investigator: Aristo team, Allen Institute for Artificial Intelligence (April 2022 - July 2025)

• My work has exposed fundamental gaps in AI’s reasoning — from DREAM on situational understanding, to mental models of everyday things, to SimpleToM on Theory of Mind. I also developed Digital Socrates, a novel framework for automatically and systemically evaluating reasoning chains in large language models by applying Socratic questioning principles. Driving transparency and accessibility in AI research, I contributed to major open-source advances like OLMo, OLMo 2, TÜLU 3, OLMoE, and OLMES. I led the development of OLMES: A Standard for Language Model Evaluations -- a completely documented, practical, open standard for reproducible language model evaluations -- which is actively used to advance various projects at Ai2 and beyond, including research on consistent ranking of models, scaling laws, and building newer open-source models.



Research Intern: Aristo team, Allen Institute for Artificial Intelligence (Summer & Fall 2021)

• When people answer questions about a specific situation, cognitive science suggests that they form a mental picture of that situation before answering. We train a new model, DREAM, to build such scene elaborations in a dataset-neutral way. We then demonstrate that using DREAM’s scene elaborations as additional context improves the answer accuracy across different downstream QA systems and on different end-tasks. Our approach is question-agnostic, leaves end-task QA models unchanged, and thus easily portable to other QA models, suggesting exciting opportunities for further improving and exploiting scene elaborations to better solve new problems.




Research assistant: Courant Institute of Mathematical Sciences, NYU (Summer 2018 - Spring 2020)

Honors Thesis Project: Detecting Event Duration in Text (Spring 2019 - Spring 2020)

• Supervised by Prof. Ernest Davis. Use various classifiers, word and sentence representations, as well as linguistics theories to automatically detect temporal relations implicitly conveyed in texts (different levels: from single event description to multiple sentences); Analyze the performance of Transformer-based state-of-the-art models in detecting implicit meaning from a psycholinguistics perspective.



Can dependency parsing help event extraction in text? (Fall 2019 - Spring 2020)

• Supervised by Prof. Ralph Grishman. Investigate the contribution of information from dependency parsing, Named Entity (NE) tagging, and Part Of Speech (POS) tagging in event extraction, beyond a baseline that uses pretrained BERT sentence representation.



Integrated Customization Environment for Information Extraction (ICE) (Summer 2019)

• Supervised by Prof. Ralph Grishman. Experiment with different classifiers, together with grammatical linguistics insights, to automatically distinguish prepositional phrases as adjuncts or arguments (achieved 88% accurate prediction of the adjunct/argument distinction using linguistics theories alone).



Termolator: A terminology extraction system (Summer 2018 - Fall 2018)

• Supervised by Prof. Adam Meyers. Refine the English Termolator's distributional metrics; Further develop the Chinese Termolator; Integrate past 5 years' developments to unify the two systems (my contributions: https://github.com/yulinggu-cs/ChineseTermolator2020, integrated to full system on July 2020).



Independent study project: Commonsense Reasoning (Summer 2018)

• Supervised by Prof. Ernest Davis. Look into English-Chinese Machine Translation failures; Design Winograd schemas and compile pronoun disambiguation problems; Toward Annotating Commonsense Inferences in Text (TACIT) annotation.




Research Intern: Human Language Technology Group (Winter 2014 - Spring 2021)

Institute for Infocomm Research, A*STAR, Singapore, Singapore

• Characterizing Singaporean, American, and British English acoustic and pronunciation patterns in children's speech using unsupervised clustering (supervised by Dr. Nancy F. Chen); Chinese tone perception in Singaporean and native Chinese Mandarin speakers; Investigating tone in whispered Mandarin (jointly supervised by Dr. Boon Pang Lim and Dr. Nancy F. Chen).

Other work experience

Courant Institute of Mathematical Sciences (CIMS), NYU

Grader for Artificial Intelligence course under Professor Ernest Davis (Fall 2019)

Grader for Basic Algorithms course under Professor Victor Shoup (Spring 2019)