深入探討大型語言模型
本課程提供大型語言模型（LLM）的發展歷程、核心技術架構、訓練模式（預訓練、微調與對齊）、多模態擴展、提示工程、思維鏈推理、智能代理，以及模型安全與隱私保護等前沿主題的全面深入介紹。
課程總覽
📚 內容摘要
本課程提供大型語言模型（LLM）演進、核心技術架構、訓練模式（預訓練、微調與對齊）、多模態擴展、提示工程、思考鏈（CoT）、代理系統，以及模型安全與隱私保護等前沿議題的全面且深入的介紹。
對全棧大型模型從預訓練到通用代理之技術演進與安全對齊的深度分析。
🎯 學習目標
- 辨別模型架構差異：識別僅編碼器（Encoder-only）、僅解碼器（Decoder-only）與編碼器-解碼器（Encoder-Decoder）模型的結構差異及其應用場景。
- 解釋 LLM 訓練流程：描述從自監督預訓練過渡到監督式微調（SFT）與人類反饋強化學習（RLHF）的轉變過程。
- 分析模型規模與行為：解釋規模法則（Scaling Laws）、突現能力（上下文學習、思考鏈）以及幻覺現象。
- 分析僅編碼器（BERT）、僅解碼器（GPT）與編碼器-解碼器（T5）架構之間的結構差異。
- 解釋三階段訓練流程：預訓練（基礎模型）、指令微調（SFT）與對齊（RLHF/PPO）。
- 比較主流 LLM（如 GPT、Llama、Qwen 與 DeepSeek）在性能、規模法則與架構創新方面的表現。
- 實施零樣本與少樣本提示策略，用於結構化資料提取與分類。
- 調校模型超參數（溫度、Top P、懲罰項），以平衡創造性與確定性輸出。
- 使用手動、自動與零樣本（「讓我們一步步思考」）方法，設計有效的思考鏈（CoT）提示。
- 分析並比較 CoT 變體：區分自我一致性、思考程式（PoT）、思維樹（ToT）與思維圖（GoT）架構。
課程 共 8 课时 · 预计 24.0h
課程
Lesson
This lesson explores the paradigm shift from task-specific AI to general-purpose Large Language Models, highlighting how scaling laws and the Transformer architecture enable emergent reasoning capabilities. Students will learn how the self-attention mechanism allows models to process data in parallel and why decoder-only architectures have become the standard for modern generative AI.
This lesson explores the evolution of Transformer architectures, highlighting why the industry has shifted toward Decoder-only models due to their superior scaling laws and generative capabilities. It also examines the foundational training pipeline, covering the transition from pre-training and Chinchilla optimality to modern instruction tuning and alignment techniques.
This lesson explores the evolution of prompting strategies, ranging from zero-shot instructions to few-shot demonstrations and Chain-of-Thought reasoning for complex logic. Students will learn how to improve model performance and reliability by using structural constraints, logical decomposition, and precise formatting to ensure outputs are suitable for programmatic use.
This lesson explores the evolution of reasoning in large language models, moving from linear Chain-of-Thought to advanced structured architectures like Tree-of-Thought and Graph-of-Thought. Students will learn how these frameworks, alongside techniques like Program of Thought and knowledge editing, enable models to perform deliberate planning, verification, and complex mathematical problem-solving.
This lesson explores the challenges of AI safety, focusing on the training paradox between model helpfulness and harmlessness, as well as the mechanics of adversarial jailbreak attacks. It also introduces statistical watermarking techniques, such as the KGW framework, which use vocabulary partitioning and logit bias to embed detectable, invisible signatures into AI-generated content.
This lesson explores the fundamental conflict in AI alignment between maintaining model helpfulness and ensuring harmlessness, highlighting how jailbreak attacks exploit this tension through role-playing and cognitive coercion. Students will learn how these vulnerabilities function and examine technical strategies, such as intent analysis and robust system prompting, to defend against prompt-based bypass attempts.
This lesson explores the evolution of Multi-modal Large Language Models (MLLMs) from vision-centric systems to integrated architectures capable of processing diverse sensory inputs like audio and 3D data. Students will learn how specialized encoders and projection bridges align non-textual signals into a unified semantic space, enabling the model to effectively reason across multiple modalities.
This lesson explores the development of autonomous GUI agents that use a tripartite architecture—planning, decision-making, and reflection—to interact with software interfaces. It further examines how Reinforcement Learning and RLHF enable these agents to adapt to dynamic environments while maintaining safety and reliability against potential risks.