Dipin Khati

According to our database, Dipin Khati authored at least 9 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering.

Daniel Rodríguez-Cárdenas, Xiaochang Li, Marcos Macedo, Antonio Mastropaolo, Dipin Khati, Yuan Tian, Huajie Shao, Denys Poshyvanyk

CoRR, January, 2026

Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis.

Dipin Khati, Daniel Rodríguez-Cárdenas, Paul Pantzer, Denys Poshyvanyk

CoRR, January, 2026

Tricky²: Towards a Benchmark for Evaluating Human and LLM Error Interactions.

Cole Granger, Dipin Khati, Daniel Rodríguez-Cárdenas, Denys Poshyvanyk

CoRR, January, 2026

2025

A Causal Perspective on Measuring, Explaining and Mitigating Smells in LLM-Generated Code.

Alejandro Velasco, Daniel Rodríguez-Cárdenas, Dipin Khati, David N. Palacio, Luftar Rahman Alif, Denys Poshyvanyk

CoRR, November, 2025

On Explaining (Large) Language Models For Code Using Global Code-Based Explanations.

David N. Palacio, Dipin Khati, Daniel Rodríguez-Cárdenas, Alejandro Velasco, Denys Poshyvanyk

CoRR, March, 2025

Mapping the Trust Terrain: LLMs in Software Engineering - Insights and Perspectives.

Dipin Khati, Yijin Liu, David N. Palacio, Yixuan Zhang, Denys Poshyvanyk

CoRR, March, 2025

Trustworthiness of Large Language Models for Code.

Dipin Khati

Proceedings of the 47th IEEE/ACM International Conference on Software Engineering, 2025

2024

Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations.

David N. Palacio, Daniel Rodríguez-Cárdenas, Alejandro Velasco, Dipin Khati, Kevin Moran, Denys Poshyvanyk

CoRR, 2024

2023

Benchmarking Causal Study to Interpret Large Language Models for Source Code.

Daniel Rodríguez-Cárdenas, David N. Palacio, Dipin Khati, Henry Burke, Denys Poshyvanyk

Proceedings of the IEEE International Conference on Software Maintenance and Evolution, 2023