Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model

arXiv:2404.16766v1 Announce Type: new
Abstract: While supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences, concerns have been raised about the depth of this alignment, with some critiques suggesting it is merely "superficial". We critically examine this hypothesis within the scope of cross-lingual generation tasks, proposing that the effectiveness of SFT may be constrained by its reliance on prior tokens to guide cross-lingual generation. Based on this crucial …

abstract alignment arxiv concerns cs.ai cs.cl english fine-tuning foundation language language model large language large language model llm sft supervised fine-tuning text type while