arxiv preprint - The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

In this episode we discuss The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning by Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, Yejin Choi. The paper discusses the effectiveness of traditional alignment tuning methods for large language models (LLMs) and introduces a new, simple tuning-free method named URIAL (Untuned LLMs with Restyled In-context ALignment). Analysis reveals that alignment tuning primarily adjusts the language style without significant transformation of the knowledge base, with the majority of decoding remaining identical to the base LLM. The proposed URIAL method, which utilizes strategic prompting and in-context learning with just a few stylistic examples, achieves comparable or superior performance to models aligned through traditional methods, questioning the necessity of complex alignment tuning and emphasizing the need for deeper understanding of LLM alignment.