works on

From the 1 of 6 linked papers with an AI index.

activity
20242026
collaborators

6 papers

cs.LG2026

Data-Efficient Adaptation of LLMs via Attention Head Reweighting

Tuomas Oikarinen, Zixiao Chen, Charlotte Siska +3

The paper introduces Attention Head Reweighting (AHR), a method that adapts large language models to new text‑classification tasks by learning a single scalar weight per attention…

cs.CR2026

Secret Scanner Agent: Extracting Secrets and Access Context from Unstructured Documents

Zixiao Chen, Mariko Wakabayashi, Charlotte Siska

Exposed documents such as emails, chat threads, tickets, and incident notes routinely leak credentials, but during incident response a leaked secret is only half the story. Respond…

cs.AI2026

CORPGEN: Simulating Corporate Environments with Autonomous Digital Employees in Multi-Horizon Task Environments

Abubakarr Jaye, Nigel Boachie Kumankumah, Chidera Biringa +8

Long-horizon reasoning is a key challenge for autonomous agents, yet existing benchmarks evaluate agents on single tasks in isolation. Real organizational work requires managing ma…

cs.CL2025

OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities

Sahil Verma, Keegan Hines, Jeff Bilmes +4

The emerging capabilities of large language models (LLMs) have sparked concerns about their immediate potential for harmful misuse. The core approach to mitigate these concerns is…

cs.CL2025

AttentionDefense: Leveraging System Prompt Attention for Explainable Defense Against Novel Jailbreaks

Charlotte Siska, Anush Sankaran

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are sus…

cs.CR2024

PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System

Gary D. Lopez Munoz, Amanda J. Minnich, Roman Lutz +17

Generative Artificial Intelligence (GenAI) is becoming ubiquitous in our daily lives. The increase in computational power and data availability has led to a proliferation of both s…