相关论文: Eliciting Language Model Behaviors with Investigat…

This study presents a comprehensive, long-term project to explore the effectiveness of various prompting techniques in detecting dialogical mental manipulation. We implement Chain-of-Thought prompting with Zero-Shot and Few-Shot settings on…

Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for…

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video…

Embodied Instruction Following (EIF) studies how autonomous mobile manipulation robots should be controlled to accomplish long-horizon tasks described by natural language instructions. While much research on EIF is conducted in simulators,…

Large language models are known to hallucinate when faced with unfamiliar queries, but the underlying mechanism that govern how models hallucinate are not yet fully understood. In this work, we find that unfamiliar examples in the models'…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…

The rapid development of large language models (LLMs) gives rise to ethical concerns about their performance, while opening new avenues for developing toxic language detection techniques. However, LLMs' unethical output and their capability…

With strong capabilities of reasoning and a broad understanding of the world, Large Language Models (LLMs) have demonstrated immense potential in building versatile embodied decision-making agents capable of executing a wide array of tasks.…

Recent advances on instruction fine-tuning have led to the development of various prompting techniques for large language models, such as explicit reasoning steps. However, the success of techniques depends on various parameters, such as…

Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization. We present a series of behavioral studies on several LLM families (LLaMA,…

With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed…

LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. Despite the success, the underlying mechanism of this…

Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration and adaptation, often…

Large Language Models (LLMs) have shown exceptional results on current benchmarks when working individually. The advancement in their capabilities, along with a reduction in parameter size and inference times, has facilitated the use of…

Capability evaluations are required to understand and regulate AI systems that may be deployed or further developed. Therefore, it is important that evaluations provide an accurate estimation of an AI system's capabilities. However, in…

This paper presents null-shot prompting. Null-shot prompting exploits hallucination in large language models (LLMs) by instructing LLMs to utilize information from the "Examples" section that never exists within the provided context to…

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain instructions, and…

Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Knowledge problem. Furthermore, we believe that large language…