Punya Syon Pandey

Punya @psyonp is an impressive UofT undergrad student. He reached out to our @JinesisLab in the 1st year of his undergrad; now as a 2nd-year undergrad, his contributed to 8 papers in our lab. 3 first-author papers at #EACL2026 #IASEAI2026 and #ICLR2026 🎉[Stellar Student Sharing]

@ZhijingJin @JinesisLab It's been a pleasure working and having the opportunity to learn so much at the @JinesisLab. Thank you for your mentorship and support throughout my research journey @ZhijingJin!

Kudos to the 1st conference paper of our undergrad RA @psyonp at #EACL2025🎉He investigates "Linguistics of LLMs" by testing multi-agent interaction quality and quantify their linguistic diversity. 📄Paper: arxiv.org/abs/2508.11915 💻Code: github.com/psyonp/core

I'm deeply grateful to my advisors @ZhijingJin and @radamihalcea, as well as my collaborators Hai Son Le and Devansh Bhardwaj for their support throughout this project at the Jinesis AI Lab at the University of Toronto. Stay tuned for our codebase!

Excited to share that our paper "SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests" has been accepted at ICLR 2026 🎉. In this work, we introduce the first adversarial evaluation benchmark specifically designed to probe sociopolitical risks in LLMs.

🔗 OpenReview: openreview.net/forum?id=xWTjM… 📄 arXiv: arxiv.org/pdf/2510.04891

@SimkoSamuel @KellinPelrine @ZhijingJin Big thanks to all our institutional support from @MPI_IS, @UofTCompSci, @VectorInst, @TorontoSRI, @CIFAR_News, @farairesearch, @ETH_en, @ETH_AI_Center. ArXiv: arxiv.org/pdf/2505.16789 GitHub: github.com/psyonp/acciden…

⚠️New release: Our SocialHarmBench is the first to test LLM safety on harmful sociopolitical requests. E.g., should #LLMs assist with creating propaganda and surveillance? 📖Paper: arxiv.org/abs/2510.04891 🙌Work by @psyonp @devansh0502 @Haisonle001 @radamihalcea @ZhijingJin

@ZhijingJin Congratulations!

Humbled to take on my 1st ACL Officer position, as Co-Chair of #ACL Ethics Committee. I look forward to promoting Responsible AI in #NLProc community & ensuring ethical research. In my term, I also hope to bridge the narrative w/ AI Safety and various social considerations of AI.

A quick look into DeepSeek’s safety guard: We find DeepSeek’s Llama Distill is >2x⚠️ as vulnerable to jailbreaking attacks as the original Llama. Seems to be a large safety risk. Stay tuned for our upcoming work @psyonp @SimkoSamuel @ZhijingJin