Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment
- URL: http://arxiv.org/abs/2405.00557v3
- Date: Mon, 8 Jul 2024 16:02:18 GMT
- Title: Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment
- Authors: Zhili Liu, Yunhao Gou, Kai Chen, Lanqing Hong, Jiahui Gao, Fei Mi, Yu Zhang, Zhenguo Li, Xin Jiang, Qun Liu, James T. Kwok,
- Abstract summary: Traditional alignment strategies rely heavily on human intervention, such asSupervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF)
We propose a novel self-alignment method that utilizes a Chain of Thought (CoT) approach, termed AlignCoT.
We introduce the Mixture of insighTful Experts (MoTE) architecture, which applies mixture of experts to enhance each component of the AlignCoT process, markedly increasing alignment efficiency.
- Score: 103.05005690990271
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: As the capabilities of large language models (LLMs) have expanded dramatically, aligning these models with human values presents a significant challenge. Traditional alignment strategies rely heavily on human intervention, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), or on the self-alignment capacities of LLMs, which usually require a strong LLM's emergent ability to improve its original bad answer. To address these challenges, we propose a novel self-alignment method that utilizes a Chain of Thought (CoT) approach, termed AlignCoT. This method encompasses stages of Question Analysis, Answer Guidance, and Safe Answer production. It is designed to enable LLMs to generate high-quality, safe responses throughout various stages of their development. Furthermore, we introduce the Mixture of insighTful Experts (MoTE) architecture, which applies mixture of experts to enhance each component of the AlignCoT process, markedly increasing alignment efficiency. The MoTE approach not only outperforms existing methods in aligning LLMs with human values but also highlights the benefits of using self-generated data, revealing the dual benefits of improved alignment and training efficiency.
Related papers
- CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation [33.33513657902765]
We propose CoEvol, an LLM-based multi-agent cooperation framework for the improvement of responses to instructions.
Empirically, models equipped with CoEvol outperform competitive baselines evaluated by MT-Bench and AlpacaEval.
arXiv Detail & Related papers (2024-06-11T08:35:37Z) - Joint Demonstration and Preference Learning Improves Policy Alignment with Human Feedback [58.049113055986375]
We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.
The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.
We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
arXiv Detail & Related papers (2024-06-11T01:20:53Z) - Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning [50.73666458313015]
Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications.
MoE has been emerged as a promising solution with its sparse architecture for effective task decoupling.
Intuition-MoR1E achieves superior efficiency and 2.15% overall accuracy improvement across 14 public datasets.
arXiv Detail & Related papers (2024-04-13T12:14:58Z) - CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment [42.71324708567498]
Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences.
We present a simple yet effective Contrastive Learning Framework for Human Alignment (CLHA) to align LLMs with human preferences directly.
arXiv Detail & Related papers (2024-03-25T11:37:15Z) - Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts [33.58165081033569]
We introduce Sparse MetA-Tuning (SMAT), a method inspired by sparse mixture-of-experts approaches.
SMAT successfully overcomes OOD sensitivity and delivers on the promise of enhancing the transfer abilities of vision foundation models.
arXiv Detail & Related papers (2024-03-13T12:46:03Z) - 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) - Enabling Language Models to Implicitly Learn Self-Improvement [49.16868302881804]
Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks.
We propose an ImPlicit Self-ImprovemenT (PIT) framework that implicitly learns the improvement goal from human preference data.
arXiv Detail & Related papers (2023-10-02T04:29:40Z) - Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration [83.4031923134958]
Corex is a suite of novel general-purpose strategies that transform Large Language Models into autonomous agents.
Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Debate, Review, and Retrieve modes.
We demonstrate that orchestrating multiple LLMs to work in concert yields substantially better performance compared to existing methods.
arXiv Detail & Related papers (2023-09-30T07:11:39Z) - Fine-tuning Language Models with Generative Adversarial Reward Modelling [30.424363135421917]
Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs)
We propose another alternative approach: Reinforcement Learning with Generative Adversarial Feedback (RLGAF) to RLHF and SFT.
arXiv Detail & Related papers (2023-05-09T17:06:06Z)
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.