Punya Syon Pandey

According to our database, Punya Syon Pandey authored at least 9 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs.

Florent Draye, Abir Harrasse, Vedant Palit, Tung-Yu Wu, Jiarui Liu, Punya Syon Pandey, Roderick Wu, Terry Jingchen Zhang, Zhijing Jin, Bernhard Schölkopf

CoRR, March, 2026

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

CoRR, February, 2026

TamperBench: Systematically Stress-Testing 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

CoRR, February, 2026

BinaryPPO: Efficient Policy Optimization for Binary Classification.

Punya Syon Pandey, Zhijing Jin

CoRR, February, 2026

Objective Matters: Fine-Tuning Objectives Shape Safety, Robustness, and Persona Drift.

Daniel Vennemeyer, Punya Syon Pandey, Phan Anh Duong, Michael Umeokoli, Samuel Ratnam

CoRR, January, 2026

CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures.

Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

Test of Time: Rethinking Temporal Signal of Benchmark Contamination.

Terry Jingchen Zhang, Gopal Dev, Ning Wang, Max Obreiter, Wenyuan Jiang, Punya Syon Pandey, Keenan Samway, Yinya Huang, Bernhard Schölkopf, Mrinmaya Sachan, Zhijing Jin

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests.

Punya Syon Pandey, Hai Son Le, Devansh Bhardwaj, Rada Mihalcea, Zhijing Jin

CoRR, October, 2025

Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected Vulnerability.

Punya Syon Pandey, Samuel Simko, Kellin Pelrine, Zhijing Jin

CoRR, May, 2025