32 citations · 34 across the 7 of their papers we have counts for
6 papers · 1 filter
Near-Miss: Latent Policy Failure Detection in Agentic Workflows
Ella Rabinovich, David Boaz, Naama Zwerdling +1
Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation of policy adherence in LLM-base…
Towards Enforcing Company Policy Adherence in Agentic Workflows
Naama Zwerdling, David Boaz, Ella Rabinovich +3
Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company p…
Exploring Straightforward Conversational Red-Teaming
George Kour, Naama Zwerdling, Marcel Zalmanovici +3
Large language models (LLMs) are increasingly used in business dialogue systems but they pose security and ethical risks. Multi-turn conversations, where context influences the mod…
Unveiling Safety Vulnerabilities of Large Language Models
George Kour, Marcel Zalmanovici, Naama Zwerdling +5
As large language models become more prevalent, their possible harmful or inappropriate responses are a cause for concern. This paper introduces a unique dataset containing adversa…
Answer Identification in Collaborative Organizational Group Chat
Naama Tepper, Naama Zwerdling, David Naori +1
We present a simple unsupervised approach for answer identification in organizational group chat. In recent years, organizational group chat is on the rise enabling asynchronous te…
Not Enough Data? Deep Learning to the Rescue!
Ateret Anaby-Tavor, Boaz Carmeli, Esther Goldbraich +5
Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a…