@psyonp profile picture
Punya Syon Pandey @psyonp
Joined February 2025
  • Tweets 10
  • Following 23
  • Followers 139
1 Photos and videos
Punya Syon Pandey retweeted
Zhijing Jin
@ZhijingJin
Feb 22
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]
6
11
287
23,307
Punya Syon Pandey retweeted
Zhijing Jin
@ZhijingJin
Feb 4
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
3
6
32
2,812
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.
2
3
12
3,968
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!
3
219
🔗 OpenReview: openreview.net/forum?id=xWTj… 📄 arXiv: arxiv.org/pdf/2510.04891
1
193
Replying to @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/accidental…
2
138
Punya Syon Pandey retweeted
Zhijing Jin
@ZhijingJin
8 Oct 2025
⚠️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
3
21
84
10,970
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
2
5
2,913
Load more