Mahavir Dabas

According to our database, Mahavir Dabas authored at least 7 papers between 2023 and 2026.

Collaborative distances:

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

2026

Memory-Induced Tool-Drift in LLM Agents.

Mahavir Dabas, Jihyun Jeong, Ming Jin, Ruoxi Jia

CoRR, May, 2026

Characterizing Model-Native Skills.

Feiyang Kang, Mahavir Dabas, Myeongseob Ko, Ruoxi Jia

CoRR, April, 2026

2025

Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks.

Mahavir Dabas, Tran Huynh, Nikhil Reddy Billa, Jiachen T. Wang, Peng Gao, Charith Peris, Yao Ma, Rahul Gupta, Ming Jin, Prateek Mittal, Ruoxi Jia

CoRR, October, 2025

DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking.

Hoang Anh Just, Mahavir Dabas, Lifu Huang, Ming Jin, Ruoxi Jia

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning.

Mahavir Dabas, Si Chen, Charles Fleming, Ming Jin, Ruoxi Jia

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Human decision-making data in the cart-pole game.

Varun Dutt, Mahavir Dabas, Shashank Uttrani, Aadhar Gupta

Dataset, July, 2024

2023

Modeling Human Actions in the Cart-Pole Game Using Cognitive and Deep Reinforcement Learning Approach.

Aadhar Gupta, Mahavir Dabas, Shashank Uttrani, Sakshi Sharma, Varun Dutt

Proceedings of the Social, Cultural, and Behavioral Modeling, 2023