NLU-11: Week 8 | Open Course Materials

This week we have two lectures on ethics and one on evaluation of large language models and alignment.

There will a tutorial on ethics this week. Please prepare answers to the following questions before your tutorial group meets:

Tutorial 3: Ethics in NLP

As a reminder, Coursework 2 has been issued and is due on Friday 21 March at 12:00 noon.

Also, the lab for next week has been released. This is a lab on prompting with GPT-3.5. It even includes a small competition on who can develop the best performing prompt on a small data set! Please note you will need an OpenAI key to run this lab; please obtain this before you attend your lab session, instructions can be found in the lab itself.

Lab 4: Prompting with GPT-3.5

Slides	Lecture	Course Content
Ethics in NLP [handout]	22	Required reading: Ethical and social risks of harm from Language Models Weidinger et al. (2021) Section 2 only Additional reading (not examinable): The Social Impact of Natural Language Processing, Hovy and Spruit (2016) An Introduction to Data Ethics, Vallor and Rewak. A Framework for Understanding Unintended Consequences of Machine Learning, Suresh and Guttag (2019) Homework: Do one of the implicit bias tests on https://implicit.harvard.edu/implicit/
Bias in Word Embeddings [handout]	23	Required reading: Semantics derived automatically from language corpora contain human-like biases, Caliskan et al. 2017 Additional reading (not examinable): Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets Irene Solaiman, Christy Dennison 2021 ETHICS WHITEPAPER: Whitepaper on Ethical Research into Large Language Models Ungless et al. 2024
In Context Learning	24	Required reading: Language Models are Few-Shot Learners Brown et al. 2020 (Sections 1,2) Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Wei et al. 2022 (Section 1,2,3) Optional: Large Language Models are Zero-Shot Reasoners Kojima et al. 2022

License

Search

Navigation