2 citations · 4 across the 7 of their papers we have counts for
5 papers · 1 filter
SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving
Erfan Baghaei Potraghloo, Saeid Shokoufa, Seyedarmin Azizi +4
Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks. Serving methods make these models faster by running even fewer experts per token,…
The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow
Arya Fayyazi, Mehdi Kamal, Massoud Pedram
Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact decides whether an action is a…
The Sharp Directions Are Against You: Curvature Analysis of Activation Steering
Seyedarmin Azizi, Arya Fayyazi, Parsa Razmara +3
Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. The stand…
Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Arya Fayyazi +2
A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the model runs, not when it is t…
Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders
Chan Aristella Lu, Arya Fayyazi, Junhao Zhang +6
Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challe…