The recent breathtaking progress made in generative natural language processing (NLP) has been propelled by large language models and innovative learning methods that intersects machine learning (ML) and NLP such as Reinforcement Learning with Human Feedback (RLHF), leading to the creation of impressive chatbots like ChatGPT. However their lack of groundedness, factuality, and interoperability with tools and custom APIs limits them to mostly creative endeavors due to low fidelity and reliability. On the contrary, digital assistants in the real world such as Siri, Alexa, and Google Assistant can interface with proprietary APIs, but they still cover a relatively narrow set of use cases that are mostly simple single-turn interactions. Through the combination of each of their strengths, the goal of deploying truly conversational and capable digital assistants that are also trustworthy seems tantalizingly close. What are the remaining challenges for this goal, and how can the ML and NLP communities come together to overcome them? The goal of this workshop is to bring together machine learning researchers and dialogue researchers from academia and industry to encourage knowledge transfer and collaboration on these central questions to discover ideas that can further expand the use cases of conversational AI. The ideal outcome of the workshop is to identify a set of concrete research directions to enable the next generation of digital assistants.
| Opening Remarks | |
| Invited Talk: New Frontiers in the Evaluation of Conversational Agents by João Sedoc (Keynote Talk) | |
| Poster & Demo Session (Poster) | |
| Invited Talk: Improving Open Language Models by Learning from Organic Interactions by Jason Weston (Keynote Talk) | |
| Invited Talk: Building a dialogue agent for Diplomacy by Emily Dinan (Keynote Talk) | |
| Lunch Break (Break) | |
| Invited Talk: LLMs with long-term memory and better factuality by Zhou Yu (Keynote Talk) | |
| Invited Talk: Embeddings and Retrieval Augmented Generation by Arvind R Neelakantan (Keynote Talk) | |
| Poster & Demo Session (Poster) | |
| Invited Talk: Safer Generative ConvAI by Pascale Fung (Keynote Talk) | |
| Invited Talk: Neuro-Symbolic Dialogue Management using Prompt-Based Transfer Learning for Dialogue Act Controlled Open-Domain NLG by Marilyn Walker (Keynote Talk) | |
| Closing Remarks | |
| Teaching Arithmetic to Small Transformers (Poster) | |
| AutoML-GPT: Large Language Model for AutoML (Poster) | |
| Can Chatbots “Understand”? Evidence of Meaning in Language Models Trained on Programs (Poster) | |
| Trust and ethical considerations in a multi-modal, explainable AI-driven chatbot tutoring system: The case of collaboratively solving Rubik’s Cube (Poster) | |
| Situated Interaction with Real-Time State Conditioning of Language Models (Poster) | |
| Scalable Conversational Moderation: Promoting Constructive Dialogue to Reduce Online Polarization (Poster) | |
| LLM Guided Inductive Inference for Solving Compositional Problems (Poster) | |
| Large Language Models can Share Images, Too! (Poster) | |
| Robustness through Loss Consistency Regularization (Poster) | |
| Let’s Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning (Poster) | |
| Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection (Poster) | |
| Assessing Spoken Language Understanding Pipeline of a Multimodal Dialogue System for Kids Learning Math at Home (Poster) | |
| Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents (Poster) | |
| DiversiGATE: A Comprehensive Framework for Reliable Large Language Models (Poster) | |
| In-Context Exemplars as Clues to Retrieving \\ from Large Associative Memory (Poster) | |
| LLM2Loss: Leveraging Language Models for Explainable Model Diagnostics (Poster) | |
| TRAC: Trustworthy Retrieval Augmented Chatbot (Poster) | |
| Conformal Prediction with Large Language Models for Multi-Choice Question Answering (Poster) | |
| Disclosing the Biases in Large Language Models via Reward Based Questioning (Poster) | |
| Can Large Language Models Reason Algorithmically in an Interactive Environment? (Poster) | |
| LMQL Chat: Scripted Chatbot Development (Poster) | |
| Idiolect: A Reconfigurable Voice Coding Assistant (Poster) | |