8 papers
BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas +2
Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedbac…
Efficient Decentralized Multi-task Dataset Valuation via Model Merging
Mohammadsajad Alipour, Mohammad Mohammadi Amiri
Accurate and efficient dataset valuation is essential for enabling fair and transparent data marketplaces, especially when multiple contributors provide data for training multi-tas…
LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas +2
Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through na…
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
Sadia Asif, Mohammad Mohammadi Amiri
Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While pr…
WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework
Xingjian Zhao, Mohammad Mohammadi Amiri, Malik Magdon-Ismail
Privacy concerns in LLMs have led to the rapidly growing need to enforce a data's "right to be forgotten". Machine unlearning addresses precisely this task, namely the removal of t…
Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes
Mohammadsajad Alipour, Mohammad Mohammadi Amiri
Large language models (LLMs) are increasingly prevalent across diverse applications. However, their enormous size limits storage and processing capabilities to a few well-resourced…
Towards Reversible Model Merging For Low-rank Weights
Mohammadsajad Alipour, Mohammad Mohammadi Amiri
Model merging aims to combine multiple fine-tuned models into a single set of weights that performs well across all source tasks. While prior work has shown that merging can approx…
Power to the Clients: Federated Learning in a Dictatorship Setting
Mohammadsajad Alipour, Mohammad Mohammadi Amiri
Federated learning (FL) has emerged as a promising paradigm for decentralized model training, enabling multiple clients to collaboratively learn a shared model without exchanging t…