CLAILGMay 23, 2025

Discovering Forbidden Topics in Language Models

arXiv:2505.17441v34 citationsh-index: 8Has Code
Originality Incremental advance
AI Analysis

This addresses the need to detect biases and alignment failures in AI systems, with incremental contributions in scaling the method to frontier and open-weight models.

The paper tackles the problem of identifying topics that language models refuse to discuss, introducing a refusal discovery method called Iterated Prefill Crawler (IPC) that retrieves 31 out of 36 forbidden topics in Tulu-3-8B within 1000 prompts and reveals censorship patterns in models like DeepSeek-R1-70B.

Refusal discovery is the task of identifying the full set of topics that a language model refuses to discuss. We introduce this new problem setting and develop a refusal discovery method, Iterated Prefill Crawler (IPC), that uses token prefilling to find forbidden topics. We benchmark IPC on Tulu-3-8B, an open-source model with public safety tuning data. Our crawler manages to retrieve 31 out of 36 topics within a budget of 1000 prompts. Next, we scale the crawler to a frontier model using the prefilling option of Claude-Haiku. Finally, we crawl three widely used open-weight models: Llama-3.3-70B and two of its variants finetuned for reasoning: DeepSeek-R1-70B and Perplexity-R1-1776-70B. DeepSeek-R1-70B reveals patterns consistent with censorship tuning: The model exhibits "thought suppression" behavior that indicates memorization of CCP-aligned responses. Although Perplexity-R1-1776-70B is robust to censorship, IPC elicits CCP-aligned refusals answers in the quantized model. Our findings highlight the critical need for refusal discovery methods to detect biases, boundaries, and alignment failures of AI systems.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes