Related papers: Feature-Guided SAE Steering for Refusal-Rate Contr…

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful content. This paper presents a novel approach to detect and…

Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve…

Large Language Models (LLMs) are widely used in Automated Essay Scoring (AES) due to their ability to capture semantic meaning. Traditional fine-tuning approaches required technical expertise, limiting accessibility for educators with…

Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes alignment a complicated procedure, sometimes producing…

Large language models (LLMs) have demonstrated remarkable capabilities; however, the optimization of their prompts has historically prioritized performance metrics at the expense of crucial safety and security considerations. To overcome…

The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become…

Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within large protein language models. Here, we employ TopK and Ordered SAEs to investigate autoregressive…

Sparse autoencoders (SAEs) have gained a lot of attention as a promising tool to improve the interpretability of large language models (LLMs) by mapping the complex superposition of polysemantic neurons into monosemantic features and…

Stance classification, the task of predicting the viewpoint of an author on a subject of interest, has long been a focal point of research in domains ranging from social science to machine learning. Current stance detection methods rely…

Large language models (LLMs) are increasingly utilized in various complex reasoning tasks due to their excellent instruction following capability. However, the model's performance is highly dependent on the open-ended characteristics of the…

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

We propose a novel zero-shot document ranking approach based on Large Language Models (LLMs): the Setwise prompting approach. Our approach complements existing prompting approaches for LLM-based zero-shot ranking: Pointwise, Pairwise, and…

Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training hyperparameter is L0: how many SAE features should fire per token on average. Existing work…

As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recognition (ASR) systems beyond rescoring n-best lists. This work…

LLM-based automatic speech recognition (ASR), a well-established approach, connects speech foundation models to large language models (LLMs) through a speech-to-LLM projector, yielding promising results. A common design choice in these…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning and text generation. However, these models can inadvertently generate unsafe or biased responses when prompted with problematic inputs, raising…

Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment…

We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation,…