4 accepted papers
Interventions in language models (LMs) are applied strategically to steer model behavior during the forward pass. Learnable interventions, also known as representation fine-tuning, aim to apply pointwise control within the concept subspace and have proven effective in altering high-level behaviors.…
Superposition refers to encoding representations of multiple features within a single neuron, which is common in deep neural networks. This property allows neurons to combine and represent multiple features, enabling the model to capture intricate information and handle complex tasks. Despite promis…
Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired during pretraining. We therefore introduce infosteer, a lightwe…
Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to their notable capabilities in planning and reasoning, LLMs have been utilized as autonomous agents for the automatic execution of various tasks. Recently, LLM-based agent systems have rapidly evolved f…