Related papers: Steering Llama 2 via Contrastive Activation Additi…
Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…
Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, particularly in terms of…
Adapting models to a language that was only partially present in the pre-training data requires fine-tuning, which is expensive in terms of both data and computational resources. As an alternative to fine-tuning, we explore the potential of…
Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs.…
Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…
Current conversational agents (CA) have seen improvement in conversational quality in recent years due to the influence of large language models (LLMs) like GPT3. However, two key categories of problem remain. Firstly there are the unique…
Controlling the behaviors of large language models (LLM) is fundamental to their safety alignment and reliable deployment. However, existing steering methods are primarily driven by empirical insights and lack theoretical performance…
This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…
Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…
Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (i.e., parametric) and external (i.e., contextual) knowledge. While substantial efforts have been made to enhance the…
Activation-based steering can personalize large language models at inference time, but its effects in educational settings remain unclear. We study persona vectors for seven character traits in short-answer generation and automated scoring…
Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…
We propose a novel framework, termed Fourier-Activated Adapter (FAA), for parameter-efficient fine-tuning of large pre-trained language models. By incorporating random Fourier features into lightweight adapter modules, FAA decomposes…
Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…
Complex social behaviors, such as empathy and strategic politeness, are widely assumed to resist the directional decomposition that makes activation steering effective for coarse attributes like sentiment or toxicity. We present STAR:…
Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…
Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…
Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…
Large Language Models (LLMs) often struggle to deliver accurate and actionable answers when user-provided information is incomplete or ill-specified. We propose a new interaction paradigm, First Ask Then Answer (FATA), in which, through…
Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factually incorrect. On the other hand, users tend to over-rely…