Prompt engineering has emerged as an indispensable technique for extending the
capabilities of large language models (LLMs) and vision-language models (VLMs). This …

Large Language Models (LLMs) have demonstrated remarkable capabilities in important
tasks such as natural language understanding and language generation, and thus have the …

Chatbots are conversational software applications designed to interact dialectically with
users for a plethora of different purposes. Surprisingly, these colloquial agents have only …

A central piece in enabling intelligent agentic behavior in foundation models is to make them
capable of introspecting upon their behavior, reasoning, and correcting their mistakes as …

In-context learning (ICL, also known as few-shot prompting) has been the standard method
of adapting LLMs to downstream tasks, by learning from a few input-output examples …

A central piece in enabling intelligent agentic behavior in foundation models is to make them
capable of introspecting upon their behavior, to reason and correct their mistakes. However …

Large language models (LLMs) have shown great potential in complex reasoning tasks, yet
their performance is often hampered by the scarcity of high-quality, reasoning-focused …

This paper investigates an under-explored challenge in large language models (LLMs):
chain-of-thought prompting with noisy rationales, which include irrelevant or inaccurate …

Requiring extensive human supervision is often impractical for continual learning due to its
cost, leading to the emergence of'name-only continual learning'that only provides the name …

In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs)
to downstream tasks using correct input-output examples. Recent advances have attempted …