JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Nasrabadi, Dom
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917801777692672
author Nasrabadi, Dom
author_facet Nasrabadi, Dom
contents We introduce JurEE, an ensemble of efficient, encoder-only transformer models designed to strengthen safeguards in AI-User interactions within LLM-based systems. Unlike existing LLM-as-Judge methods, which often struggle with generalization across risk taxonomies and only provide textual outputs, JurEE offers probabilistic risk estimates across a wide range of prevalent risks. Our approach leverages diverse data sources and employs progressive synthetic data generation techniques, including LLM-assisted augmentation, to enhance model robustness and performance. We create an in-house benchmark comprising of other reputable benchmarks such as the OpenAI Moderation Dataset and ToxicChat, where we find JurEE significantly outperforms baseline models, demonstrating superior accuracy, speed, and cost-efficiency. This makes it particularly suitable for applications requiring stringent content moderation, such as customer-facing chatbots. The encoder-ensemble's modular design allows users to set tailored risk thresholds, enhancing its versatility across various safety-related applications. JurEE's collective decision-making process, where each specialized encoder model contributes to the final output, not only improves predictive accuracy but also enhances interpretability. This approach provides a more efficient, performant, and economical alternative to traditional LLMs for large-scale implementations requiring robust content moderation.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08442
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles
Nasrabadi, Dom
Machine Learning
Artificial Intelligence
We introduce JurEE, an ensemble of efficient, encoder-only transformer models designed to strengthen safeguards in AI-User interactions within LLM-based systems. Unlike existing LLM-as-Judge methods, which often struggle with generalization across risk taxonomies and only provide textual outputs, JurEE offers probabilistic risk estimates across a wide range of prevalent risks. Our approach leverages diverse data sources and employs progressive synthetic data generation techniques, including LLM-assisted augmentation, to enhance model robustness and performance. We create an in-house benchmark comprising of other reputable benchmarks such as the OpenAI Moderation Dataset and ToxicChat, where we find JurEE significantly outperforms baseline models, demonstrating superior accuracy, speed, and cost-efficiency. This makes it particularly suitable for applications requiring stringent content moderation, such as customer-facing chatbots. The encoder-ensemble's modular design allows users to set tailored risk thresholds, enhancing its versatility across various safety-related applications. JurEE's collective decision-making process, where each specialized encoder model contributes to the final output, not only improves predictive accuracy but also enhances interpretability. This approach provides a more efficient, performant, and economical alternative to traditional LLMs for large-scale implementations requiring robust content moderation.
title JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.08442