Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

• URL: http://arxiv.org/abs/2305.03047v2
• Date: Sat, 2 Dec 2023 21:36:10 GMT
• Title: Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
• Authors: Zhiqing Sun, Yikang Shen, Qinhong Zhou, Hongxin Zhang, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan
• Abstract summary: Recent AI-assistant agents, such as ChatGPT, rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback to align the output with human intentions. This dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision. We propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision.
• Score: 84.31474052176343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of large language models (LLMs) with human intentions, ensuring they are helpful, ethical, and reliable. However, this dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision and the related issues on quality, reliability, diversity, self-consistency, and undesirable biases. To address these challenges, we propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision. Our approach encompasses four stages: first, we use an LLM to generate synthetic prompts, and a topic-guided method to augment the prompt diversity; second, we use a small set of human-written principles for AI models to follow, and guide the LLM through in-context learning from demonstrations (of principles application) to produce helpful, ethical, and reliable responses to user's queries; third, we fine-tune the original LLM with the high-quality self-aligned responses so that the resulting model can generate desirable responses for each query directly without the principle set and the demonstrations anymore; and finally, we offer a refinement step to address the issues of overly-brief or indirect responses. Applying SELF-ALIGN to the LLaMA-65b base language model, we develop an AI assistant named Dromedary. With fewer than 300 lines of human annotations (including < 200 seed prompts, 16 generic principles, and 5 exemplars for in-context learning). Dromedary significantly surpasses the performance of several state-of-the-art AI systems, including Text-Davinci-003 and Alpaca, on benchmark datasets with various settings.

Related papers

• Can We Trust AI Agents? An Experimental Study Towards Trustworthy LLM-Based Multi-Agent Systems for AI Ethics [10.084913433923566]
  This study examines how trustworthiness-enhancing techniques affect ethical AI output generation. We design the prototype LLM-BMAS, where agents engage in structured discussions on real-world ethical AI issues. Discussions reveal terms like bias detection, transparency, accountability, user consent, compliance, fairness evaluation, and EU AI Act compliance.
  arXiv  Detail & Related papers  (2024-10-25T20:17:59Z)
• Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models [46.09562860220433]
  We introduce GazeReward, a novel framework that integrates implicit feedback -- and specifically eye-tracking (ET) data -- into the Reward Model (RM) Our approach significantly improves the accuracy of the RM on established human preference datasets.
  arXiv  Detail & Related papers  (2024-10-02T13:24:56Z)
• MACAROON: Training Vision-Language Models To Be Your Engaged Partners [95.32771929749514]
  Large vision-language models (LVLMs) generate detailed responses even when questions are ambiguous or unlabeled. In this study, we aim to shift LVLMs from passive answer providers to proactive engaged partners. We introduce MACAROON, self-iMaginAtion for ContrAstive pReference OptimizatiON, which instructs LVLMs to autonomously generate contrastive response pairs for unlabeled questions.
  arXiv  Detail & Related papers  (2024-06-20T09:27:33Z)
• Aligning Large Language Models from Self-Reference AI Feedback with one General Principle [61.105703857868775]
  We propose a self-reference-based AI feedback framework that enables a 13B Llama2-Chat to provide high-quality feedback. Specifically, we allow the AI to first respond to the user's instructions, then generate criticism of other answers based on its own response as a reference. Finally, we determine which answer better fits human preferences according to the criticism.
  arXiv  Detail & Related papers  (2024-06-17T03:51:46Z)
• Human-Instruction-Free LLM Self-Alignment with Limited Samples [64.69906311787055]
  We propose an algorithm that can self-align large language models (LLMs) iteratively without active human involvement. Unlike existing works, our algorithm relies on neither human-crafted instructions nor labeled rewards, significantly reducing human involvement. We show that our method can unlock the LLMs' self-generalization ability to perform alignment with near-zero human supervision.
  arXiv  Detail & Related papers  (2024-01-06T14:00:12Z)
• Exploration with Principles for Diverse AI Supervision [88.61687950039662]
  Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. This strong reliance on human oversight poses a significant hurdle to the advancement of AI innovation. We propose a novel paradigm termed Exploratory AI (EAI) aimed at autonomously generating high-quality training data.
  arXiv  Detail & Related papers  (2023-10-13T07:03:39Z)
• SALMON: Self-Alignment with Instructable Reward Models [80.83323636730341]
  This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision. We develop an AI assistant named Dromedary-2 with only 6 exemplars for in-context learning and 31 human-defined principles.
  arXiv  Detail & Related papers  (2023-10-09T17:56:53Z)
• Aligning Large Language Models through Synthetic Feedback [43.84431341195111]
  We propose a novel alignment learning framework with synthetic feedback not dependent on extensive human annotations. In human evaluation, our model is preferred to Alpaca and Dolly-v2, 55.0% and 58.5% of the time, respectively.
  arXiv  Detail & Related papers  (2023-05-23T06:41:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.