Deconstructing In-Context Learning: Understanding Prompts via Corruption

arXiv:2404.02054v1 Announce Type: new
Abstract: The ability of large language models (LLMs) to "learn in context" based on the provided prompt has led to an explosive growth in their use, culminating in the proliferation of AI assistants such as ChatGPT, Claude, and Bard. These AI assistants are known to be robust to minor prompt modifications, mostly due to alignment techniques that use human feedback. In contrast, the underlying pre-trained LLMs they use as a backbone are known to be brittle …

abstract ai assistants arxiv assistants bard chatgpt claude context corruption cs.cl growth in-context learning language language models large language large language models learn llms prompt prompts robust type understanding via