Hallucination, leakage, and prompt injection are observable operational risks. Alignment theory asks which guarantees hold under specific formal assumptions. They require different evidence. Lectures 22 and 26 therefore have separate teaching guides, without turning one theorem into a universal impossibility claim.
The first half of L06 is about ethics. Yen-Lung Tsai quotes Karpathy's line that hallucination is a feature of LLMs, then works through plagiarism, whether your data gets used for training, and DeepSeek's censorship and corpus skew, and closes with seven principles of responsible use. The second half is about applications: give the model the right information and clear instructions, and one system prompt becomes a Lucky Vicky positivity generator, a social-media copywriter, or a biased college-major counselor. The week-6 assignment moves that prompt into an OpenAI-compatible API with a Gradio front end: a chatbot with a persona.
An LLM will confidently answer that Oppenheimer was born in 1967 (the year he died). RAG retrieves first and generates second. The first 60 pages of Hung-Yu Kao's Fall 2025 RAG deck are all about finding the right material. Sparse vectors (bag-of-words, TF-IDF, BM25) are cheap and dependable; dense vectors catch paraphrases. BERT's [CLS] isn't a good sentence vector as-is, hence Sentence-BERT pooling and bi-encoders. A cross-encoder is accurate but needs nearly 50 million passes for 10,000 sentences, while a bi-encoder needs 20,000. SimCSE uses dropout as data augmentation, DPR beats BM25 with only 1,000 training examples, and GTR shows that scaling up a dual encoder improves out-of-domain retrieval.
Models trained on large amounts of web data have three kinds of problems, each paired with a goal. Bias comes from the model attending to the majority and sacrificing minorities, and the goal is fairness; bias can enter at any step from data to evaluation, and can be addressed through data, the loss function, or interface design. Harmful content sits in the long tail of the data distribution, and the goal is safety; safeguards can be placed at four levels (training data, input, training, and output), and jailbreaking is the attempt to get around them. For hallucination the goal is factuality; a long answer can be split into minimal claims that are checked one by one, and that score can be fed back to train the model. The usual corrective for all three is alignment, yet a reward model is imperfect, optimizing against it too far makes things worse, and preference data carries biases of its own.
A deep research agent produces a report—maybe thousands of words with dozens of citations. How do you score it? Using LLMs as judges is biased, asking humans is too expensive, and benchmarks can't keep up. STC and other recent approaches try to solve this from the 'confidence' angle—but there's no perfect answer yet.
2023 was the first full academic year after ChatGPT, and LLMs rewrote the NLP conference agenda. ACL's Best Papers examined humor understanding and the propagation of political bias; an EMNLP Best Paper explained in-context learning through information flow; and the HackAPrompt competition paper also won an EMNLP Best Paper award, signaling that security research had entered the mainstream. The year's largest shift was from asking how to make models more accurate to asking how we can tell when a model is misleading us.
2023 was the first year in which LLMs comprehensively rewrote the AI research agenda. DPO received a NeurIPS Outstanding Paper Runner-Up award, ReAct became an ICLR Oral, and hallucination grew from a marginal term into a major track at every conference. Meanwhile, 3D Gaussian Splatting swept through computer vision after its SIGGRAPH debut, Mamba emerged at the end of the year to challenge the Transformer attention monopoly, and publication volume for traditional NLP pipelines began a clear decline.
Numbers are the easiest part of an LLM report to hallucinate. I therefore put every trusted number into a SHA-256-addressed evidence manifest and let the LLM cite only {{fact.id}} placeholders. If it writes a bare number, the entire output is discarded and replaced with a deterministic template.
Lecture 16 divides NLP's social impact into four questions: why models hallucinate, why AI-assisted creativity may homogenize output, how work is reorganized, and why value alignment cannot be reduced to one reward.
The [WikiChat paper](https://aclanthology.org/2023.findings-emnlp.157/) expands RAG into query formulation, retrieval, filtering, generation, claim extraction, renewed retrieval and verification, and removal of unsupported content—and evaluates retrieval separately from factuality.