Related papers: Steer Model beyond Assistant: Controlling System P…

System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt…

Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of…

Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts…

Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising performance, recent work shows that it can be unreliable or…

Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data,…

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ensemble has attracted…

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Language models generate functionally correct code that tends toward excessive verbosity, with elaborate documentation and defensive patterns that diverge from human baselines. Two prompting mechanisms have emerged for stylistic control:…

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of…

Large language models are highly sensitive to prompts, but this sensitivity is usually studied through task-relevant instructions, demonstrations, or reasoning cues. In this paper, we study a different form of prompt sensitivity: whether…

Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt…

A key component of modern conversational systems is the Dialogue State Tracker (or DST), which models a user's goals and needs. Toward building more robust and reliable DSTs, we introduce a prompt-based learning approach to automatically…

Rapidly increasing model scales coupled with steering methods such as chain-of-thought prompting have led to drastic improvements in language model reasoning. At the same time, models struggle with compositional generalization and are far…

Large language models (LLMs) exhibit robust capabilities in text generation and comprehension, mimicking human behavior and exhibiting synthetic personalities. However, some LLMs have displayed offensive personality, propagating toxic…

We propose Prefix-Adaptive Decoding (PREADD), a flexible method for controlled text generation. Unlike existing methods that use auxiliary expert models to control for attributes, PREADD does not require an external model, instead relying…

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training…

Language models are trained to follow instructions, but they are also powerful pattern completers. What happens when these two objectives conflict? We construct conversations in which a user instruction to behave in a target way T (e.g.,…