Punya Syon Pandey

Researcher, Department of Computer Science, University of Toronto

Joined

March 2025

Names

Punya Syon Pandey (Preferred)

Emails

****@mail.utoronto.ca (Confirmed)

Personal Links

DBLP

Semantic Scholar

Career & Education History

Researcher

Department of Computer Science, University of Toronto (utoronto.ca)

2024 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

causal reasoning

large language models

AI alignment

Present

Publications

Training with Honeypots: Reshaping How LLMs Fail
Samuel Simko, Punya Syon Pandey, Zhijing Jin, Bernhard Schölkopf
- ICML 2026
- Readers: Everyone
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
- ICLR 2026 Workshop RSI ShortPaper
- Readers: Everyone
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
- CAO Poster
- Readers: Everyone
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Nayeema Nonta, Matthew Kowal, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
- ICLR 2026 AIWILD
- Readers: Everyone
Training with Honeypots: Reshaping How LLMs Fail
Samuel Simko, Punya Syon Pandey, Zhijing Jin, Bernhard Schölkopf
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Preserving Historical Truth: Detecting Historical Revisionism in Large Language Models
Francesco Ortu, Joeun Yook, Punya Syon Pandey, Keenan Samway, Bernhard Schölkopf, Alberto Cazzaniga, Rada Mihalcea, Zhijing Jin
- AI4Peace
- Readers: Everyone
SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
Punya Syon Pandey, Lê Hải Sơn, Devansh Bhardwaj, Rada Mihalcea, Zhijing Jin
- AI4Peace
- Readers: Everyone
CauSciBench: A Comprehensive Benchmark on End-to-End Causal Inference for Scientific Research
Sawal Acharya, Terry Jingchen Zhang, Andrew Kim, Anahita Haghighat, Sun Xianlin, Pepijn Cobben, Rahul Babu Shrestha, Maximilian Mordig, Jacob T. Emmerson, Furkan Danisman, Yuen Chen, Clijo Jose, Andrei Ioan Muresanu, Justin Cui, Jiarui Liu, Yahang Qi, Punya Syon Pandey, Yinya Huang, Bernhard Schölkopf, Mrinmaya Sachan et al. (1 additional authors not shown)
- Submitted to ICLR 2026
- Readers: Everyone
SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
Punya Syon Pandey, Lê Hải Sơn, Devansh Bhardwaj, Zhijing Jin
- ICLR 2026 Poster
- Readers: Everyone
Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
Punya Syon Pandey, Samuel Simko, Kellin Pelrine, Zhijing Jin
- Submitted to ICLR 2026
- Readers: Everyone

View all 13 publications

Co-Authors

View all 37 co-authors