Abstractive Red-Teaming of Language Model Character

2026-02-12

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We want language model assistants to conform to a character specification, which asserts how the model should act across diverse user interactions. While models typically follow these character specifications, they can occasionally violate them in large-scale deployments. In this work, we aim to identify types of queries that are likely to produce such character violations at deployment, using much less than deployment-level compute. To do this, we introduce abstractive red-teaming, where we search for natural-language query categories, e.g."The query is in Chinese. The query asks about family roles,"that routinely elicit violations. These categories abstract over the many possible variants of a query which could appear in the wild. We introduce two algorithms for efficient category search against a character-trait-specific reward model: one based on reinforcement learning on a category generator LLM, and another which leverages a strong LLM to iteratively synthesize categories from high-scoring queries. Across a 12-principle character specification and 7 target models, we find that our algorithms consistently outperform baselines, and generate qualitatively interesting categories; for example, queries which ask Llama-3.1-8B-Instruct to predict the future lead to responses saying that AI will dominate humanity, and queries that ask GPT-4.1-Mini for essential prison survival items lead to enthusiastic recommendation of illegal weapons. Overall, we believe our results represent an important step towards realistic pre-deployment auditing of language model character.

Problem

• character violation
• language model
• red-teaming
• query categories
• pre-deployment auditing

Innovation

• abstractive red-teaming
• character specification
• category generation
• reward model
• pre-deployment auditing