2024

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

We introduce WildGuard -- an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal rate. …

Position Paper: A Roadmap to Pluralistic Alignment

With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an open …

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

The ability to derive underlying principles from a handful of observations and then generalize to novel situations---known as inductive reasoning---is central to human intelligence. Prior work suggests that language models (LMs) often fall short on …

The Generative AI Paradox: "What It Can Create, It May Not Understand"

The recent wave of generative AI has sparked unprecedented global attention, with both excitement and concern over potentially superhuman levels of artificial intelligence: models now take only seconds to produce outputs that would challenge or …

Value Kaleidoscope: Engaging AI 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 …

Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing

It is commonly perceived that the strongest language models (LMs) rely on a combination of massive scale, instruction data, and human feedback to perform specialized tasks -- e.g., summarization and paraphrasing, without supervision. In this paper, …

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models

It is commonly perceived that the strongest language models (LMs) rely on a combination of massive scale, instruction data, and human feedback to perform specialized tasks -- e.g., summarization and paraphrasing, without supervision. In this paper, …