5 citations · 10 across the 6 of their papers we have counts for
4 papers · 1 filter
BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate
Arnon Mazza, Elad Levi
Deploying guardrails for custom policies remains challenging, as generic safety models fail to capture task-specific requirements, while prompting LLMs suffers from inconsistent bo…
IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems
Elad Levi, Ilan Kadar
Large Language Models (LLMs) are transforming artificial intelligence, evolving into task-oriented systems capable of autonomous planning and execution. One of the primary applicat…
Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases
Elad Levi, Eli Brosh, Matan Friedmann
Prompt engineering is a challenging and important task due to the high sensitivity of Large Language Models (LLMs) to the given prompt and the inherent ambiguity of a textual task…
Stay on topic with Classifier-Free Guidance
Guillaume Sanchez, Honglu Fan, Alexander Spangher +3
Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrat…