1

BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations of Implied Social Biases

Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework that …

Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms

Commonsense norms are defeasible by context: reading books is usually great, but not when driving a car. While contexts can be explicitly described in language, in embodied scenarios, contexts are often provided visually. This type of visually …

Value Kaleidoscope: Engaging Machines with Pluralistic Human Values, Rights, and Duties

Human values are crucial to human decision-making. Value pluralism is the view that multiple correct values may be held in tension with one another (e.g., when considering lying to a friend to protect their feelings, how does one balance honesty with …

Quark: Controllable Text Generation with Reinforced Unlearning

Large-scale language models often learn behaviors that are misaligned with user expectations. Generated text may contain offensive or toxic language, contain significant repetition, or be of a different sentiment than desired by the user. We consider …

Can Machines Learn Morality? The Delphi Experiment

As AI systems become increasingly powerful and pervasive, there are growing concerns about machines' morality or a lack thereof. Yet, teaching morality to machines is a formidable task, as morality remains among the most intensely debated questions …

ProsocialDialog: A Prosocial Backbone for Conversational Agents

Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them. To address this issue, we introduce ProsocialDialog, the first large-scale multi-turn dialogue dataset …

''I'm Not Mad'': Commonsense Implications of Negation and Contradiction

Natural language inference requires reasoning about contradictions, negations, and their commonsense implications. Given a simple premise (e.g., "I'm mad at you"), humans can reason about the varying shades of contradictory statements ranging from …

EnglishBot: A Conversational System for Second Language Learning

Today, many students learn to speak a foreign language by listening to and repeating pre-recorded materials. This is due to the lack of practice opportunities with human partners. Leveraging recent advancements in AI, Speech, and NLP, we developed …

BookBuddy: Turning Digital Materials Into Interactive Foreign Language Lessons Through a Voice Chatbot

Digitization of education has brought a tremendous amount of online materials that are potentially useful for language learners to practice their reading skills. However, these digital materials rarely help with conversational practice, a key …

QuizBot: A Dialogue-based Adaptive Learning System for Factual Knowledge

Advances in conversational AI have the potential to enable more engaging and effective ways to teach factual knowledge. To investigate this hypothesis, we created QuizBot, a dialogue-based agent that helps students learn factual knowledge in science, …