Curriculum Vitae
View PDF
shashwatnow@gmail.com
Education
ELLIS, Max Planck Institute for Intelligent Systems, Tübingen
Topic: Scaling Supervision for AI Advisors: Jonas Geiping and Douwe Kiela
International Institute of Information Technology (IIIT), Hyderabad
GPA: 9.60/10
Thesis: New Frontiers for Machine Unlearning, advised by Prof. Ponnurangam K.
Experience
Project: Scalable Oversight
Mentor: Dan Hendrycks
Project: AutoML for Tree-based and linear ensembles to find alpha across datasets
Advisors: Jerome Lang, Dominik Peters
Mentor: Tanmoy Chakroborty
Mentors: Matteo Monti, Rachid Guerraroui
Mentors: Mikel Forcada, Jorge Gracia
Publications
Answer Matching Outperforms Multiple Choice for Language Model Evaluations
Nikhil Chandak*, Shashwat Goel*, Ameya Prabhu, Moritz Hardt, Jonas Geiping
ICML Assessing World Models Workshop, 2025.Pitfalls in Evaluating Language Model Forecasters
Daniel Paleka*, Shashwat Goel*, Jonas Geiping, Florian Tramèr
ICML Assessing World Models Workshop, 2025.Measuring Belief Updates in Curious Agents
Joschka Strüber, Ilze Amanda Auzina, Shashwat Goel, Susanne Keller, Jonas Geiping, Ameya Prabhu, Matthias Bethge
(Oral) ICML Assessing World Models Workshop, 2025.Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation
Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru, Jonas Geiping, Matthias Bethge, Ameya Prabhu
(Oral) ICLR Scaling Self Improving Models Workshop, COLM, 2025.
[webpage], [code], [data]Great Models Think Alike and this Undermines AI Oversight
Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna Chandra, P. Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping
(Spotlight) ICML, 2025.
[code], [tool], [data]Corrective Machine Unlearning
Shashwat Goel*, Ameya Prabhu*, Philip Torr, P. Kumaraguru, Amartya Sanyal
TMLR, 2024.
[twitter], [code]The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
Center for AI Safety, Scale AI
ICML, 2024.
[media], [webpage], [code]Proportional Aggregation of Preferences for Sequential Decision Making
Nikhil Chandak, Shashwat Goel, Dominik Peters
(Outstanding Paper Award) AAAI, 2024.
[twitter], [talk]Representation Engineering: A Top-Down Approach to AI Transparency
Center for AI Safety
ArXiv, 2023.
[talk], [webpage], [code]
- denotes equal contribution.
Honours and Awards
- Outstanding Paper Award (Top 3/12,000+), AAAI 2024
- Outstanding Reviewer (Top 10%): ICML 2022, ICLR DMLR Workshop 2024
- Finalist (Top 50/3000+), ACM-ICPC Indian Regionals, 2020
- Honorable Mention, International Olympiad of Linguistics, 2019
- National Rank 6, International Olympiad of Informatics Indian Team Selection, 2019
- Grand Prize Winner (1/1500+), NASA Ames Space Settlement Design Contest, 2017
Teaching Experience
- Head Teaching Assistant, Responsible and Safe AI, IIIT Hyderabad, Spring 2024
- Facilitator, AI Safety Fundamentals, BlueDot Impact, Spring 2023
- Teaching Assistant, Topics in DL (Graph Neural Networks), IIIT Hyderabad, Spring 2023
- Teaching Assistant, Automata Theory, IIIT Hyderabad, Fall 2022
Academic Service and Outreach
- Reviewer: CoLLAs 2024, ICLR DMLR Workshop 2024, AISTATS 2024, CoLLAs 2023, CODS-COMAD 2023, ICML 2022
- Trainer, Indian Team Selection for the International Olympiad of Informatics (IOI) 2020
University Groups
- ML Reading Group @IIIT-H (Founder)
- Effective Altruism Group @IIIT-H (Founder)
- Theory Group @IIIT-H (Former Admin)
- Programming Club @IIIT-H (Former Admin)
- Parliamentary Debate Team @IIIT-H
- Ping! Student Magazine @IIIT-H (Editor)
last updated: July 23, 2024