References

AI Notes prioritizes public primary papers, benchmark papers, standards, and official project documentation. A reference indicates useful further reading; individual pages explain which claim or design question it supports.

Language Models and Transformers

• Vaswani et al. (2017), Attention Is All You Need
• Sennrich et al. (2016), Neural Machine Translation of Rare Words with Subword Units
• Kudo and Richardson (2018), SentencePiece
• Brown et al. (2020), Language Models are Few-Shot Learners
• Ouyang et al. (2022), Training language models to follow instructions with human feedback
• Liu et al. (2023), Lost in the Middle

Retrieval and Embeddings

• Reimers and Gurevych (2019), Sentence-BERT
• Karpukhin et al. (2020), Dense Passage Retrieval
• Lewis et al. (2020), Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Thakur et al. (2021), BEIR

Agents and Tools

• Yao et al. (2022), ReAct
• Schick et al. (2023), Toolformer
• Park et al. (2023), Generative Agents
• Packer et al. (2023), MemGPT
• LangChain documentation
• LangGraph documentation
• Pydantic documentation

Evaluation and Grounding

• Lin et al. (2021), TruthfulQA
• Liang et al. (2022), HELM
• Min et al. (2023), FActScore
• Zheng et al. (2023), Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
• Es et al. (2023), RAGAS
• Saad-Falcon et al. (2023), ARES
• NIST AI Risk Management Framework
• Malkov and Yashunin (2016), Hierarchical Navigable Small World Graphs
• Schulhoff et al. (2023), Ignore This Title and HackAPrompt

Reference Policy

References must be public and independently accessible. Private archives, working conversations, and unpublished internal material are not accepted as public citations. Pages should distinguish a source-backed statement from an editorial recommendation or engineering heuristic.