Related papers: Steering Language Models With Activation Engineeri…

Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language models. Yet even…

Pretrained large language models have become indispensable for solving various natural language processing (NLP) tasks. However, safely deploying them in real world applications is challenging because they generate toxic content. To address…

Accent variability remains a major errors in automatic speech recognition, yet most adaptation methods rely on parameter fine-tuning without understanding where accent information is encoded. We treat accent variation as an interpretable…

Emotional prompting - the use of specific emotional diction in prompt engineering - has shown increasing promise in improving large language model (LLM) performance, truthfulness, and responsibility. However these studies have been limited…

Organizations increasingly deploy separate purpose-built AI tools across professional domains, often hiring domain specialists for each, recreating the staffing models AI was expected to transform. Yet the meta-skills that make these tools…

Vision-Language-Action (VLA) models have demonstrated remarkable generalization capabilities in robotic manipulation tasks, yet their substantial computational overhead remains a critical obstacle to real-world deployment. Improving…

Since language models are used to model a wide variety of languages, it is natural to ask whether the neural architectures used for the task have inductive biases towards modeling particular types of languages. Investigation of these biases…

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…

Large language models (LLMs), optimized through human feedback, have rapidly emerged as a leading paradigm for developing intelligent conversational assistants. However, despite their strong performance across many benchmarks, LLM-based…

As foundation models grow in capability, the ability to efficiently and reliably control their behavior becomes critical. Fine-tuning these models can be costly, and while prompting can be practical for controllability, it remains fragile…

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…

Limited data for low-resource languages typically yield weaker language models (LMs). Since pre-training is compute-intensive, it is more pragmatic to target improvements during fine-tuning. In this work, we examine the use of Active…

We present Test-Driven AI Agent Definition (TDAD), a methodology that treats agent prompts as compiled artifacts: engineers provide behavioral specifications, a coding agent converts them into executable tests, and a second coding agent…

Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at…

Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer…

Simulating realistic driving behavior is crucial for developing and testing autonomous systems in complex traffic environments. Equally important is the ability to control the behavior of simulated agents to tailor scenarios to specific…

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Language models (LMs) can be directed to perform target tasks by using labeled examples or natural language prompts. But selecting examples or writing prompts for can be challenging--especially in tasks that involve unusual edge cases,…

This case study investigates the task of job classification in a real-world setting, where the goal is to determine whether an English-language job posting is appropriate for a graduate or entry-level position. We explore multiple…

This paper investigates prior prompt engineering (pPE) in the context of reinforcement fine-tuning (RFT), where language models (LMs) are incentivized to exhibit behaviors that maximize performance through reward signals. While existing RFT…