Publications

(2024). NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers. The 31st International Conference on Computational Linguistics (COLING 2025).

Cite NYT-Connections (dataset)

(2024). Can We Afford The Perfect Prompt? Balancing Cost and Accuracy with the Economical Prompting Index. The 31st International Conference on Computational Linguistics (COLING 2025).

Cite Code

(2024). STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024, Oral Presentation, Social Impact Paper Award).

Cite Arxiv Code Dataset

(2024). MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024).

Cite Arxiv MirrorStories!

(2024). Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Student Research Workshop) (ACL SRW 2024).

Cite ACL Anthology Code

(2024). Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Cite ACL Anthology Arxiv Code

(2024). Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024, Oral Presentation).

Cite ACL Anthology Arxiv Code

(2024). Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Cite ACL Anthology Arxiv Code

(2024). EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024).

Cite EvoGrad

(2024). WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts. European Chapter of the Association for Computational Linguistics (EACL 2024, Oral Presentation).

Cite Arxiv ACL Anthology Code Video

(2023). Natural Language Processing: Current Methods and Challenges. In Engineering Mathematics and AI.

Cite DOI Textbook

(2023). The Turing Quest: Can Transformers Make Good NPCs?. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) (ACL SRW 2023).

Cite ACL Anthology Code

(2023). Debiasing should be good and bad: Measuring the consistency of debiasing techniques in language models. Findings of the Association for Computational Linguistics: ACL 2023 (ACL Findings 2023).

Cite ACL Anthology Arxiv Code Video

(2022). An application of pseudo-log-likelihoods to natural language scoring. arXiv preprint arXiv:2201.09377.

Cite ArXiv

(2021). Predicting irregularities in arrival times for transit buses with recurrent neural networks using GPS coordinates and weather data. Journal of Ambient Intelligence and Humanized Computing.

Cite Springer

(2021). ADEPT: An Adjective-Dependent Plausibility Task. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (ACL-IJCNLP 2021, Oral Presentation).

Cite ACL Anthology Code Video

(2020). An analysis of dataset overlap on winograd-style tasks. Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020).

Cite ACL Anthology ArXiv Code

(2018). The KnowRef coreference corpus: Removing gender and number cues for difficult pronominal anaphora resolution. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019).

Cite ACL Anthology ArXiv Code

(2018). How reasonable are common-sense reasoning tasks: A case-study on the Winograd schema challenge and SWAG. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019).

Cite ACL Anthology Arxiv Code

(2018). A knowledge hunting framework for common sense reasoning. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018).

Cite ACL Anthology ArXiv Code

(2018). A generalized knowledge hunting framework for the winograd schema challenge. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop (NAACL 2018, Best Paper Award).

Cite ACL Anthology Video

(2017). Behavioral patterns and associations with glucose control during 12-week randomized free-living clinical trial of day and night hybrid closed-loop insulin delivery in adults with type 1 diabetes. Diabetes technology & therapeutics.

Cite PubMed

(2016). Modeling glucagon action in patients with type 1 diabetes. IEEE journal of biomedical and health informatics.

Cite PubMed

(2016). Efficacy of single-hormone and dual-hormone artificial pancreas during continuous and interval exercise in adult patients with type 1 diabetes: randomised controlled crossover trial. Diabetologia.

Cite Springer

(2016). Comparison of two continuous glucose monitoring systems, Dexcom G4 Platinum and Medtronic Paradigm Veo Enlite System, at rest and during exercise. Diabetes technology & therapeutics.

Cite PubMed

(2015). The efficacy of single-and dual-hormone artificial pancreas systems at regulating glucose levels during continuous and interval exercise in type 1 diabetes. Canadian Journal of Diabetes.

Cite CJD

(2015). Enhancing glucose sensor models: modeling the drop-outs. Diabetes Technology & Therapeutics.

Cite PubMed

(2014). Practical Approach to Physical-Chemical Acid-Base Management: Stewart at the Bedside. Annals of the American Thoracic Society.

Cite PubMed