Cite
Lee, Bruce W., et al. Programming Refusal with Conditional Activation Steering. arXiv:2409.05907, arXiv, 17 Feb. 2025. arXiv.org, https://doi.org/10.48550/arXiv.2409.05907.
Metadata
Title: Programming Refusal with Conditional Activation Steering Authors: Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, Erik Miehling, Pierre Dognin, Manish Nagireddy, Amit Dhurandhar Cite key: lee2025Programming
Links
Abstract
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selective responses are essential, such as content moderation or domain-specific assistants. In this paper, we propose Conditional Activation Steering (CAST), which analyzes LLM activation patterns during inference to selectively apply or withhold activation steering based on the input context. Our method is based on the observation that different categories of prompts activate distinct patterns in the model’s hidden states. Using CAST, one can systematically control LLM behavior with rules like “if input is about hate speech or adult content, then refuse” or “if input is not about legal advice, then refuse.” This allows for selective modification of responses to specific content while maintaining normal responses to other content, all without requiring weight optimization. We release an open-source implementation of our framework at github.com/IBM/activation-steering .
Notes
From Obsidian
(As notes and annotations from Zotero are one-way synced, this section include a link to another note within Obsidian to host further notes)
Programming-Refusal-with-Conditional-Activation-Steering
From Zotero
(one-way sync from Zotero) Imported: 2025-06-27 Comment: ICLR 2025, Spotlight View in local Zotero
Annotations
Highlighting colour codes
Link to original
- Note: highlights for quicker reading or comments stemmed from reading the paper but might not be too related to the paper
- External Insight: Insights from other works but was mentioned in the paper
- Question/Critic: questions or comments on the content of paper
- Claim: what the paper claims to have found/achieved
- Finding: new knowledge presented by the paper
- Important: anything interesting enough (findings, insights, ideas, etc.) that’s worth remembering
From Zotero
(one-way sync from Zotero)