8 papers
Evaluating Large Language Models on Solved and Unsolved Problems in Graph Theory: Implications for Computing Education
Adithya Kulkarni, Mohna Chakraborty, Jay Bagga
Large Language Models are increasingly used by students to explore advanced material in computer science, including graph theory. As these tools become integrated into undergraduat…
Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios
Mohna Chakraborty, Adithya Kulkarni, Qi Li
Prompt-based methods leverage the knowledge of pre-trained language models (PLMs) trained with a masked language modeling (MLM) objective; however, these methods are sensitive to t…
Empirical Analysis for Unsupervised Universal Dependency Parse Tree Aggregation
Adithya Kulkarni, Oliver Eulenstein, Qi Li
Dependency parsing is an essential task in NLP, and the quality of dependency parsers is crucial for many downstream tasks. Parsers' quality often varies depending on the domain an…
An Empirical Study of Using ChatGPT for Fact Verification Task
Mohna Chakraborty, Adithya Kulkarni, Qi Li
ChatGPT has recently emerged as a powerful tool for performing diverse NLP tasks. However, ChatGPT has been criticized for generating nonfactual responses, raising concerns about i…
Beryllium: Neural Search for Algorithm Implementations
Adithya Kulkarni, Mohna Chakraborty, Yonas Sium +3
In this paper, we explore the feasibility of finding algorithm implementations from code. Successfully matching code and algorithms can help understand unknown code, provide refere…
Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts
Mohna Chakraborty, Adithya Kulkarni, Qi Li
Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment cla…
CPTAM: Constituency Parse Tree Aggregation Method
Adithya Kulkarni, Nasim Sabetpour, Alexey Markin +2
Diverse Natural Language Processing tasks employ constituency parsing to understand the syntactic structure of a sentence according to a phrase structure grammar. Many state-of-the…
Truth Discovery in Sequence Labels from Crowds
Nasim Sabetpour, Adithya Kulkarni, Sihong Xie +1
Annotation quality and quantity positively affect the learning performance of sequence labeling, a vital task in Natural Language Processing. Hiring domain experts to annotate a co…