Workshop on Instruction Tuning and Instruction Following


@ NeurIPS 2023, Dec 15
Room 220-222, Ernest N. Morial Convention Center
New Orleans, Louisiana, United States

Quick Links: Twitter | OpenReview Portal | NeurIPS Site
Program: Speakers | Panelists | Organization | Schedule

Contact Us: an-instructive-workshop@googlegroups.com


Announcements


1. Recordings are available on the NeurIPS website (NeurIPS registration required). They will be made public after one month (Jan 2024).
2. Talk slides are posted on the speakers page.
3. Congratuations to paper award winners!
4. Workshop highlights and photos can be found on our Twitter.

Thank you for joining us at NeurIPS 2023! Hope to see you next time!


Recent advancements in training large language models (LLMs) to follow “instructions” have significantly increased their ability to comprehend open-ended language commands, encompassing a wide range of needs, preferences, and values.

This remarkable transformation has led to the creation of remarkable industrial models such as GPT-4 and Bard, as well as an increased focus within the open-source and research communities: creating new benchmark and resources [1,2], developing new training methods [3,4], and understanding the limitations of these methods [5]. Furthermore, instruction following powered by LLMs has proven to be effective in multi-modal settings, with applications in image editing [6] and robotic command execution [7].

We organize this workshop to facilitate discussions on advancing instruction tuning methodologies and constructing general-purpose instruction-following models. We believe it is crucial to organize this workshop due to the prevalence of proprietary models with restricted access, thereby creating the need for an open platform to encourage discussions. Moreover, we aim to foster interdisciplinary collaboration by bringing together researchers from diverse fields such as natural language processing, computer vision, robotics, human-computer interaction, AI safety, among others, to share their latest findings and explore potential avenues for future research.

Centering on “instructions,” we invite submissions covering various topics, including but not limited to the list below:


Speakers

Check talk details (title, abstract, speaker bio, slides) at this page!

Name 6

Tatsunori Hashimoto
Stanford University
9:00-9:30

Name 2

Nazneen Rajani
(Formerly)
Hugging Face
9:30-10:00

Name 5

Fei Xia
Google DeepMind
10:15-10:45

Name 4

Sara Hooker
Cohere for AI
14:00-14:30

Name 1

Alex Tamkin
Anthropic
14:30-15:00

Panel 1

Key Techniques, Insights, and Challenges in Building Instruction-following Models

Time: 10:45-11:30

Name 1

Alex Tamkin
Anthropic

Name 5

Fei Xia
Google DeepMind

Name 3

Albert Webson
Google DeepMind
University of Tokyo

Name 3

Prithviraj (Raj) Ammanabrolu
UC San Diego
MosaicML

Panel 2

Open and Collaborative Strategies for Large Language Model Adaptation

Time: 15:15-16:00

Name 2

Nazneen Rajani
(Formerly)
Hugging Face

Name 6

Tatsunori Hashimoto
Stanford University

Name 3

Hao Zhang
UC San Diego
lmsys.org

Name 6

Colin Raffel
University of Toronto
Vector Institute

Paper Awards

Best Paper
  1. Delve into PPO: Implementation Matters for Stable RLHF
    Rui Zheng, Shihan Dou, Songyang Gao, Yuan Hua, Wei Shen, Binghai Wang, Yan Liu, Senjie Jin, Yuhao Zhou, Limao Xiong, Lu Chen, Zhiheng Xi, Nuo Xu, Wenbin Lai, Minghao Zhu, Haoran Huang, Tao Gui, Qi Zhang, Xuanjing Huang
  2. Learning Interactive Real-World Simulators
    Sherry Yang, Yilun Du, Seyed Kamyar Seyed Ghasemipour, Jonathan Tompson, Dale Schuurmans, Pieter Abbeel
Honorable Mention
  1. Understanding Hidden Context in Preference Learning: Consequences for RLHF
    Anand Siththaranjan, Cassidy Laidlaw, Dylan Hadfield-Menell
  2. Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
    Sam Toyer, Olivia Watkins, Ethan Mendes, Justin Svegliato, Luke Bailey, Tiffany Wang, Isaac Ong, Karim Elmaaroufi, Pieter Abbeel, Trevor Darrell, Alan Ritter, Stuart Russell
  3. Understanding the Effects of RLHF on LLM Generalisation and Diversity
    Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina, Eric Hambro, Edward Grefenstette, Roberta Raileanu
  4. Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks
    Lingfeng Sun, Devesh Jha, Chiori Hori, Siddarth Jain, Radu Corcodel, Xinghao Zhu, Masayoshi Tomizuka, Diego Romeres
  5. Self-RAG: Self-reflective Retrieval Augmented Generation
    Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi
  6. FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
    Seonghyeon Ye, Doyoung Kim, Sungdong Kim, Hyeonbin Hwang, Seungone Kim, Yongrae Jo, James Thorne, Juho Kim, Minjoon Seo

Organizers

Name 1 Qinyuan Ye

University of Southern California

Name 2

Yizhong Wang
University of Washington

Name 3

Shayne Longpre
Massachusetts Institute of Technology

Name 4

Yao Fu
University of Edinburgh

Name 5

Daniel Khashabi
Johns Hopkins University

Steering Committee

Name 1

Hannaneh Hajishirzi
University of Washington
Allen Institute for AI

Name 2

Xiang Ren
University of Southern California
Allen Institute for AI

Name 3

Robin Jia
University of Southern California

Sponsors