Human-Instruction-Free LLM Self-Alignment with Limited Samples
Aligning large language models (LLMs) with human values is a vital task for LLM practitioners. Current alignment techniques have several limitations: (1) requiring a large amount of annotated data; (2) demanding heavy human involvement; (3) lacking a systematic mechanism to continuously improve. In this work, we study aligning LLMs to a new domain with limited samples (e.g. < 100). We propose an algorithm that can self-align LLMs iteratively without active human involvement. Unlike existing works, our algorithm relies on neither human-crafted instructions nor labeled rewards, significantly reducing human involvement. In addition, our algorithm can self-improve the alignment continuously. The key idea is to first retrieve high-quality samples related to the target domain and use them as In-context Learning examples to generate more samples. Then we use the self-generated samples to finetune the LLM iteratively. We show that our method can unlock the LLMs' self-generalization ability to perform alignment with near-zero human supervision. We test our algorithm on three benchmarks in safety, truthfulness, and instruction-following, and show good performance in alignment, domain adaptability, and scalability.
Code (0)
등록된 구현이 없습니다.
Tasks
In-Context LearningInstruction FollowingSimilar Papers 제목 키워드 기반
A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation
Large multimodal models still struggle with text-rich images because of inadequate training data. Self-Instruct provides an annotation-free way for generating instruction data, but its quality is poor, as multimodal alig…
Image CaptioningDynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models
Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs…
Self-Judge: Selective Instruction Following with Alignment Self-Evaluation
Pre-trained large language models (LLMs) can be tailored to adhere to human instructions through instruction tuning. However, due to shifts in the distribution of test-time data, they may not always execute instructions …
Instruction FollowingSemantic SimilaritySemantic Textual SimilaritySelf-Instruct: Aligning Language Models with Self-Generated Instructions
Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instr…
Instruction FollowingLanguage ModellingSelf-Alignment with Instruction Backtranslation
We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, st…
Instruction FollowingLanguage ModelingLanguage Modelling