Computer Science > Computation and Language
[Submitted on 21 Jun 2024]
Title:Steering Without Side Effects: Improving Post-Deployment Control of Language Models
View PDF HTML (experimental)Abstract:Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model queries are unproblematic and frequent retraining results in unstable user experience, methods for mitigation of worst-case behavior should be targeted. One such method is classifying inputs as potentially problematic, then selectively applying steering vectors on these problematic inputs, i.e. adding particular vectors to model hidden states. However, steering vectors can also negatively affect model performance, which will be an issue on cases where the classifier was incorrect. We present KL-then-steer (KTS), a technique that decreases the side effects of steering while retaining its benefits, by first training a model to minimize Kullback-Leibler (KL) divergence between a steered and unsteered model on benign inputs, then steering the model that has undergone this training. Our best method prevents 44% of jailbreak attacks compared to the original Llama-2-chat-7B model while maintaining helpfulness (as measured by MT-Bench) on benign requests almost on par with the original LM. To demonstrate the generality and transferability of our method beyond jailbreaks, we show that our KTS model can be steered to reduce bias towards user-suggested answers on TruthfulQA. Code is available: this https URL.
Submission history
From: Asa Cooper Stickland [view email][v1] Fri, 21 Jun 2024 01:37:39 UTC (624 KB)
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.