Appendix 3: References

Sources cited in Chapters 4 to 7 are collected here by chapter, in the order they were cited. References for Chapters 1 to 3 currently remain at the end of those chapters until the publisher-reviewed Word versions are backported; the Apress edition gathers all of them alphabetically in Appendix References.

Chapter 4

  1. Ouyang et al. Training Language Models to Follow Instructions with Human Feedback. 2022.
  2. Wang et al. Self-Instruct: Aligning Language Models with Self-Generated Instructions. 2022.
  3. Hugging Face. Chat Templating documentation.
  4. Hugging Face TRL. SFTTrainer documentation.
  5. Hu et al. LoRA: Low-Rank Adaptation of Large Language Models. 2021.
  6. Dettmers et al. QLoRA: Efficient Finetuning of Quantized Language Models. 2023.
  7. Schulman et al. Proximal Policy Optimization Algorithms. 2017.
  8. Williams. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. 1992.
  9. Rafailov et al. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. 2023.
  10. Hong et al. ORPO: Monolithic Preference Optimization without Reference Model. 2024.
  11. Schick et al. Toolformer: Language Models Can Teach Themselves to Use Tools. 2023.
  12. Qin et al. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs. 2023.
  13. Patil et al. Gorilla: Large Language Model Connected with Massive APIs. 2023.
  14. OpenAI. Function Calling documentation.
  15. OpenAI. Introducing Structured Outputs in the API. 2024.
  16. Lewis et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. 2020.
  17. Lightman et al. Let’s Verify Step by Step. 2023.
  18. Wang et al. Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations. 2023.
  19. Shao et al. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. 2024.
  20. Liu et al. Understanding R1-Zero-Like Training: A Critical Perspective (Dr. GRPO). 2025.
  21. Zheng et al. Group Sequence Policy Optimization. 2025.
  22. Yu et al. DAPO: An Open-Source LLM Reinforcement Learning System at Scale. 2025.
  23. Yan et al. Learning to Reason under Off-Policy Guidance (LUFFY). 2025.
  24. Zelikman et al. STaR: Bootstrapping Reasoning With Reasoning. 2022.
  25. Zhang et al. ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search. 2024.
  26. Hinton et al. Distilling the Knowledge in a Neural Network. 2015.
  27. Kim, Rush. Sequence-Level Knowledge Distillation. 2016.
  28. Chen et al. Knowledge Distillation of Black-Box Large Language Models. 2024.

Chapter 5

References

  1. Vaswani et al. Attention Is All You Need. 2017.
  2. Devlin et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. 2019.
  3. Raffel et al. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5). 2020.
  4. Radford et al. Improving Language Understanding by Generative Pre-Training (GPT). 2018.
  5. Radford et al. Language Models are Unsupervised Multitask Learners (GPT-2). 2019.
  6. Brown et al. Language Models are Few-Shot Learners (GPT-3). 2020.
  7. Ouyang et al. Training Language Models to Follow Instructions with Human Feedback (InstructGPT). 2022.
  8. Chowdhery et al. PaLM: Scaling Language Modeling with Pathways. 2022.
  9. Touvron et al. LLaMA: Open and Efficient Foundation Language Models. 2023.
  10. Touvron et al. Llama 2: Open Foundation and Fine-Tuned Chat Models. 2023.
  11. Bai et al. Qwen Technical Report. 2023.
  12. Qwen Team. Qwen2 Release Notes. 2024.
  13. Qwen Team. Qwen2.5 Release Notes. 2024.
  14. Jiang et al. Mistral 7B. 2023.
  15. Jiang et al. Mixtral of Experts. 2024.
  16. Du et al. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. 2022.
  17. DeepSeek-AI. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model. 2024.
  18. DeepSeek-AI. DeepSeek-V3 Technical Report. 2024.
  19. DeepSeek-AI. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. 2025.
  20. Parmar et al. Nemotron-4 340B Technical Report. 2024.
  21. OpenCompass. A Universal Evaluation Platform for Foundation Models. 2023.
  22. Gao et al. A Framework for Few-Shot Language Model Evaluation (lm-evaluation-harness). 2023.
  23. Liang et al. Holistic Evaluation of Language Models (HELM). 2023.
  24. Hugging Face. Open LLM Leaderboard. 2023.
  25. Chiang et al. Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference (LMSYS). 2024.
  26. Papers with Code. Machine Learning Research & Benchmarks. 2019.
  27. Hendrycks et al. Measuring Massive Multitask Language Understanding (MMLU). 2021.
  28. Rein et al. GPQA: A Graduate-Level Google-Proof Q&A Benchmark. 2023.
  29. Suzgun et al. Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them (BBH). 2022.
  30. Cobbe et al. Training Verifiers to Solve Math Word Problems (GSM8K). 2021.
  31. Hendrycks et al. Measuring Mathematical Problem Solving with the MATH Dataset. 2021.
  32. Chen et al. Evaluating Large Language Models Trained on Code (HumanEval). 2021.
  33. Austin et al. Program Synthesis with Large Language Models (MBPP). 2021.
  34. Jimenez et al. SWE-bench: Can Language Models Resolve Real-World GitHub Issues?. 2024.
  35. Zheng et al. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. 2023.
  36. Dubois et al. AlpacaFarm / AlpacaEval: An Automatic Evaluator for Instruction-Following Models. 2023.
  37. Lin, Hilton, Evans. TruthfulQA: Measuring How Models Mimic Human Falsehoods. 2022.
  38. Shi et al. Language Models are Multilingual Chain-of-Thought Reasoners (MGSM). 2022.
  39. Clark et al. TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages. 2020.
  40. Artetxe, Ruder, Yogatama. On the Cross-lingual Transferability of Monolingual Representations (XQuAD). 2020.
  41. Bai et al. LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding. 2023.
  42. Kamradt. Needle in a Haystack — Pressure Testing LLMs. 2023.
  43. Yue et al. MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark. 2024.
  44. Lu et al. MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts. 2023.
  45. Liu et al. MMBench: Is Your Multi-modal Model an All-around Player?. 2023.

Chapter 6

  1. NVIDIA. H100 Tensor Core GPU Datasheet. 2023.
  2. Dao et al. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. 2022.
  3. Kwon et al. Efficient Memory Management for Large Language Model Serving with PagedAttention. 2023.
  4. Ainslie et al. GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints. 2023.
  5. vLLM Project. vLLM Documentation (Automatic Prefix Caching, Chunked Prefill, Structured Outputs, Disaggregated Prefilling). 2024.
  6. NVIDIA. TensorRT-LLM Documentation (In-Flight Batching, Paged KV Cache, Chunked Prefill, Guided Decoding, Speculative Decoding). 2024.
  7. SGLang Team. SGLang Documentation (RadixAttention, Structured Outputs, Quantized KV Cache, LoRA Serving, PD Disaggregation). 2024.
  8. Hugging Face. Text Generation Inference Documentation (Continuous Batching, Paged Attention, Guidance, Monitoring). 2024.
  9. Chen et al. Accelerating Large Language Model Decoding with Speculative Sampling. 2023.
  10. Cai et al. Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. 2024.
  11. Wang et al. Self-Consistency Improves Chain of Thought Reasoning in Language Models. 2023.
  12. Zhang et al. H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models. 2023.
  13. Xiao et al. Efficient Streaming Language Models with Attention Sinks. 2023.
  14. Li et al. SnapKV: LLM Knows What You Are Looking For Before Generation. 2024.
  15. Liu et al. KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache. 2024.
  16. Hooper et al. KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization. 2024.
  17. Lin et al. AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. 2024.
  18. Xiao et al. SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models. 2023.
  19. Frantar et al. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. 2023.
  20. PyTorch Blog. Quantization-Aware Training for Large Language Models with PyTorch. 2024.
  21. Frantar & Alistarh. SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot. 2023.

Chapter 7

  1. OpenAI. A Practical Guide to Building Agents. 2025.
  2. Anthropic. Building Effective Agents. 2024.
  3. Anthropic. Effective Context Engineering for AI Agents. 2025.
  4. Anthropic. Equipping Agents for the Real World with Agent Skills. 2025.