Shailja Thakur

Research Scientist IBM Research

My current work is on agentic AI — evaluation, debugging, harness optimization, and context management for multi-step systems. Earlier work spans LLMs for code and hardware design automation, security, and interpretability.

Publications

19
ACL
2026
Think Like You Execute: Verifiable Chain of Thought from Program Traces
Shailja Thakur, Vaibhav Saxena, Rohan Kulkarni, Shivdeep Singh, Parameswaran Selvam, Hiroshi Kanayama, Hima Patel
Paper/arXiv
ACL Findings
2026
STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs
Sungeun An, Swanand Ravindra Kadhe, Shailja Thakur, Chad DeLuca, Hima Patel
Paper
arXiv
2026
The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance
Shailja Thakur, Sungeun An, Chad DeLuca, Hima Patel
arXiv
arXiv
2026
A Systematic Approach for Large Language Models Debugging
Basel Shbita, Anna Lisa Gentile, Bing Zhang, Sungeun An, Shailja Thakur, Shubhi Asthana, Yi Zhou, Saptha Surendran, Farhan Ahmed, Rohan Kulkarni, Yuya Jeremy Ong, Chad DeLuca, Hima Patel
arXiv
TODAES
2025
Can EDA Tool Feedback Improve Verilog Generation by LLMs?
Jason Blocklove, Shailja Thakur, Benjamin Tan, Hammond Pearce, Siddharth Garg, Ramesh Karri
arXiv
TODAES
2024
VeriGen: A Large Language Model for Verilog Code GenerationBest Paper
Shailja Thakur, Baleegh Ahmad, Hammond Pearce, Benjamin Tan, Brendan Dolan-Gavitt, Ramesh Karri, Siddharth Garg
Project/HuggingFace/arXiv/Award
ACM TCPS
2022
CANOA: CAN Origin Authentication Through Power Side-Channel Monitoring
Shailja Thakur, Carlos Moreno, Sebastian Fischmeister
Project/arXiv
IEEE TIFS
2023
On Hardware Security Bug Code Fixes By Querying Large Language Models
Baleegh Ahmad, Shailja Thakur, Benjamin Tan, Ramesh Karri, Hammond Pearce
arXiv
IEEE TIFS
2023
LLM-assisted Generation of Hardware Assertions
Rahul Kande, Hammond Pearce, Benjamin Tan, Brendan Dolan-Gavitt, Shailja Thakur, Ramesh Karri, Jeyavijayan Rajendran
arXiv
DAC
2024
AutoChip: Automating HDL Generation Using LLM Feedback
Shailja Thakur, Jason Blocklove, Hammond Pearce, Benjamin Tan, Siddharth Garg, Ramesh Karri
arXiv
ICCAD
2024
Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTS
Matthew DeLorenzo, Animesh Basak Chowdhury, Vasudev Gohil, Shailja Thakur, Siddharth Garg, Ramesh Karri, Jeyavijayan Rajendran
arXiv
NeurIPS
2023
Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT
Akshaj Kumar Veldanda, Fabian Grob, Shailja Thakur, Hammond Pearce, Benjamin Tan, Ramesh Karri, Siddharth Garg
arXiv
ICCAD
2023
Towards the ImageNets of ML4EDA
Animesh Chowdhury, Shailja Thakur, Hammond Pearce, Ramesh Karri, Siddharth Garg
arXiv
DATE
2023
Benchmarking Large Language Models for Automated Verilog RTL Code GenerationBest Paper Nominee
Shailja Thakur, Baleegh Ahmad, Zhenxing Fan, Hammond Pearce, Benjamin Tan, Ramesh Karri, Brendan Dolan-Gavitt, Siddharth Garg
Project/HuggingFace/arXiv
DATE
2023
Security and Interpretability in Automotive Systems
Shailja Thakur, Sebastian Fischmeister
arXiv
ICPR
2020
Saliency-map based model explanation
Shailja Thakur, Sebastian Fischmeister
Project/Paper
ICPR
2020
Generalizable Saliency map-based explanation
Shailja Thakur, Sebastian Fischmeister
Project/arXiv
BuildSys
2014
Wattshare: Detailed energy apportionment in shared living spaces within commercial buildings
Shailja Thakur, Manaswi Saha, Amarjeet Singh, Yuvraj Agarwal
Paper
e-Energy
2014
EnergyLens: Combining Smartphones with Electricity Meter for Accurate Activity Detection and User Annotation
Manaswi Saha, Shailja Thakur, Amarjeet Singh, Yuvraj Agarwal
Paper