When querying a large language model (LLM), the context, i.e. personal,
demographic, and cultural information specific to an end-user, can
significantly shape the response of the LLM. For example, asking the model to
explain Newton's second law with the context "I am a toddler" yields a
different answer compared to the context "I am a physics professor." Proper
usage of the context enables the LLM to generate personalized responses,
whereas inappropriate contextual influence can lead to stereotypical and
potentially harmful generations (e.g. associating "female" with "housekeeper").
In practice, striking the right balance when leveraging context is a nuanced
and challenging problem that is often situation-dependent. One common approach
to address this challenge is to fine-tune LLMs on contextually appropriate
responses. However, this approach is expensive, time-consuming, and not
controllable for end-users in different situations. In this work, we propose
Context Steering (CoS) - a simple training-free method that can be easily
applied to autoregressive LLMs at inference time. By measuring the contextual
influence in terms of token prediction likelihood and modulating it, our method
enables practitioners to determine the appropriate level of contextual
influence based on their specific use case and end-user base. We showcase a
variety of applications of CoS including amplifying the contextual influence to
achieve better personalization and mitigating unwanted influence for reducing
model bias. In addition, we show that we can combine CoS with Bayesian
Inference to quantify the extent of hate speech on the internet. We demonstrate
the effectiveness of CoS on state-of-the-art LLMs and benchmarks.

通过测量预测标记的可能性以及调控它，我们提出了适用于自动回归 LL 模型的简单无需训练的方法，被称为 CoS （Context Steering），使实践者能够根据其特定用例和终端用户群确定适当的上下文影响水平，并展示了 CoS 的各种应用，包括增强上下文影响以实现更好的个性化和减少模型偏差所产生的无用影响，此外，还展示了如何结合贝叶斯推断来量化互联网上的仇恨言论，我们在最先进的 LL 模型和基准测试上展示了 CoS 的有效性。