Neisarg Dave, Ph.D.

Education

Doctor of Philosophy

College of  Information Sciences and Technology

The Pennsylvania State University 

Advisors : C. Lee Giles, Daniel Kifer, Ankur Mali

Bachelor of Engineering (Hons.)

Electrical and Electronics Engineering

BITS Pilani, K.K. Birla Goa Campus

Research

Keywords: Large Language Models, Agentic AI, Neurosymbolic AI, LLM Evaluation, Document Understanding, Explainable and Trustworthy AI, Formal Methods

My dissertation research focused on investigating the gaps in theoretical expressivity and empirical learnability of RNNs, transformers and Large Language Models. Specifically, I concentrated on tasks rooted in Chomsky's Hierarchy, which provides a well understood framework for employing formal methods to gauge the limits of learnability. Additionally, I explored the robustness of learned representations by extracting rules as finite state machines from neural networks, and comparing their stability across various grammars, network architectures, initialization methods and training styles. 

Building on my PhD research, I work on neurosymbolic and agentic LLM systems: grounding language models in knowledge graphs, LLM-guided code generation, evaluation and guardrails for agents, and multimodal document understanding. I am especially interested in reasoning models, state space models, and world models.

Recent Activities

• [November 2026] Paper on What the Trading Desk Knows: Knowledge and Practice Gaps in LLM Option Valuation under review at the AAAI 2027 Workshop on Financial Foundation Models (FinFM).

• [October 2026] Paper on Stability and Fidelity of Symbolic Rule Extraction from Recurrent Neural Networks under review at TMLR.

• [August 2026] Joined Mathpix as Senior Machine Learning Research Engineer, working on multimodal document layout models.

• [Spring 2026] Graduate Project Advisor for Columbia University IEOR E4524, mentoring M.S. students on LLMs for financial research and question answering.

• [Sept 8, 2025] Poster presented on A Learnability Study of RNNs on Counter and Dyck Languages at NeSy 2025 at UC Santa Cruz.

• [Nov 22, 2024]  Gave a talk on Exploring the Limits: Current AI Models and Augmented Systems at NEC Labs America, Princeton

• [August 26, 2024] Joined ADP Innovation Labs as Lead Data Scientist

• [August 19, 2024] Defended Ph.D. on Analyzing the Stability, Learnability, and Precision of Symbolic Structures by Neural Networks. 

• [July 28, 2024] Gave a talk on Neurosymbolic and Verifiable AI: Stability, Learnability and Precision at Samsung Research America, Irvine

• [June 4, 2024] Investigating Symbolic Capabilities of Large Language Models accepted for oral presentation at LNSAI-IJCAI 2024 

• [May 23, 2024]   Paper on Investigating Symbolic Capabilities of Large Language Models is out on arXiv

• [May 11, 2024]   Presenting poster on Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Network  at the Workshop on BGPT, ICLR 2024

• [April 5, 2024]   Giving a talk on Building Foundations of Neurosymbolic and Verifiable AI: A stability and precision perspective at AI+X seminar, University of South Florida

• [April 2, 2024] Presenting poster on Investigation into Math Solving Abilities of LLM based AI Systems at AI Week, Penn State.