English

Discovering Forbidden Topics in Language Models

Computation and Language 2025-06-12 v3 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2505.17441,
  title  = {Discovering Forbidden Topics in Language Models},
  author = {Can Rager and Chris Wendler and Rohit Gandikota and David Bau},
  journal= {arXiv preprint arXiv:2505.17441},
  year   = {2025}
}
R2 v1 2026-07-01T02:33:04.432Z