Introduction[edit]

That being said, welcome to the MLC NLP interest group! We're a very welcoming group who meets every Sunday 9 AM PST to discuss NLP papers, discuss ongoing projects, and provide feedback to each other. We're a very diverse group ranging from little to several years of experience in the field so don't hesitate to join regardless of past experience - there'll always be something to learn. We have published a few papers and blog posts in the past - if you're interested in learning more about what we do, consider joining our discord or checking out some of the past presentations and work we've done! Link to join discord - discord.gg/nNJ4GBPZm9


Reading Group Day & Time	Sunday, 9am PST
Channel:	`#natural-language-processing`

Previous Meetings[edit]

Date	Paper Title	Presenter	Presentation
Dec 3'23	OpenAI Assistant API and function calling	Akash	Recording
Nov 5'23	Query Rewriting for Retrieval-Augmented Large Language Models	Aishwarya	Recording
Oct 29 '23	Self-Refine: Iterative Refinement with Self-Feedback	Jay	Recording
Oct 22 '23	Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection	Aiswarya	Slides Recording
Oct 15 '23	Decomposing Language Models Into Understandable Components	Aiswarya	Slides Recording
Oct 1 '23	A Survey on Large Language Model based Autonomous Agents Part 2	Akash	Recording
Sep 24 '23	A Survey on Large Language Model based Autonomous Agents Part 1	Aiswarya	Slides Recording
Sep 10 '23	Direct Preference Optimization	Atsushi	Slides Recording
Sep 3 '23	Giraffe: Adventures in Expanding Context Lengths in LLMs	Aiswarya	Slides
Aug 27 '23	Gorilla: Large Language Model Connected with Massive APIs	Aiswarya	Slides
July - Aug '23	Finetuning LLM Project
Jun 18 '23	QLora code discussion	Akash	Recording
Jun 4 '23	QLoRA: Efficient Finetuning of Quantized LLMs	Jay	Recording
May 28 '23	Self-Instruct: Aligning Language Models with Self-Generated Instructions	Aiswarya	Slides Recording
May 21 '23	PeFT: Parameter-Efficient Fine-Tuning	Jay	Recording
Apr 30 '23	LoRA: Low-Rank Adaptation of Large Language Models	Pavan	Slides Recording
Apr 23 '23	Sparks of Artificial General Intelligence: Early experiments with GPT-4 PART 2	Jay	Recording
Apr 9 '23	Sparks of Artificial General Intelligence: Early experiments with GPT-4 PART 1	Akash	Recording
Apr 2 '23	Successive Prompting for Decomposing Complex Questions	Aiswarya	Recording
Mar 26 '23	Mixture of Soft Prompts for Controllable Data Generation	Jay	Recording
Mar 19 '23	Kubeflow and MLOps	pappachuck	Recording
Mar 12 '23	How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection	Akash	Slides Recording
Feb 26 '23	Meeting for Unit test generator and Meme Generation project
Feb 19 '23	MemPrompt: Memory-assisted Prompt Editing with User Feedback	Aiswarya	Slides Recording
Feb 5 '23	Automating Code Review Activities by Large-Scale Pre-training	Aiswarya	Slides Recording
Jan 29 '23	Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation	Jay & Akash	Slides Recording
Jan 22 '23	Cramming: Training a Language Model on a Single GPU in One Day	Jay	Slides Recording
Jan 15 '23	RLHF and InstructGPT	Akash & Aiswarya	Slides Recording
Dec 18	Fine Tuning Language Models to find agreement among humans with diverse preferences	Aiswarya	Link
Dec 11	Cicero: Human-level play in the game of Diplomacy by combining language models with strategic reasoning	Akash	Link
Dec 4	Scaling Instruction Fine Tuned Language Models	Jay	Link
Nov 27	Large Language Models can Self Improve	Aiswarya	Link
Nov 20	Mind's Eye: Grounded Language Model Reasoning through Simulation	Akash	Link
Nov 13	Large Language Models are Human Level Prompt Engineers	Aiswarya	Link
Nov 6	Language-Mediated Robot Task Planning	David Fagan	Link
Oct 16	Measuring and Improving Consistency in Pretrained Language Models	Aiswarya	Link
Oct 9	Locating and Editing Factual Associations in GPT	Aiswarya	Link
Sept 18	Knowledge Neurons in Pretrained Transformers	Jay	Link
Sept 4	A Mathematical Framework for Transformer Circuits	Aiswarya	Link
Aug 28	Data Distributional Properties Drive Emergent In-Context Learning in Transformers	Akash Kumar	Link
Aug 21	GenIE: Generative Information Extraction	Aiswarya	Link
Aug 14	HydraSum	Aiswarya	Link
Aug 7	Autoregressive Entity Retrieval	Adithya	Link

Completed Projects[edit]

Title	Description	Completion Date
ICLR Blog Post	Select a previous ICLR paper and write an informal and accessible blog post. Highlight ambiguities, provide better visualization, etc.	04/10/2022

ICLR Blog Post Submissions[edit]

An Understanding of Learning from Demonstrations for Neural Text Generation

Authors: Aiswarya Sankar, Pavan Kantharaju

Discovering Non-Monotonic Autoregressive Ordering for Text Generation Models using Sinkhorn Distributions

Author: Ashutosh Kumar

... More to come

Additional presentations -

and many others! Please check out our notion page if you're interested in watching the recordings for past meetings.

If you think you have a paper suggestion which you'd like to present or discuss, come and join us on discord :)