Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
OLMES: A Standard for Language Model Evaluations
Progress in AI is often demonstrated by new models claiming improved performance on tasks measuring model capabilities. Evaluating language models in particular is challenging, as small changes to…
SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals
Language agents powered by large language models (LLMs) are increasingly valuable as decision-making tools in domains such as gaming and programming. However, these agents often face challenges in…
Digital Socrates: Evaluating LLMs through explanation critiques
While LLMs can provide reasoned explanations along with their answers, the nature and quality of those explanations are still poorly understood. In response, our goal is to define a detailed way of…
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
Real-world robotic tasks stretch over extended horizons and encompass multiple stages. Learning long-horizon manipulation tasks, however, is a long-standing challenge, and demands decomposing the…
A Design Space for Intelligent and Interactive Writing Assistants
In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge…
Mitigating Barriers to Public Social Interaction with Meronymous Communication
In communities with social hierarchies, fear of judgment can discourage communication. While anonymity may alleviate some social pressure, fully anonymous spaces enable toxic behavior and hide the…
PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers
With the rapid growth of scholarly archives, researchers subscribe to"paper alert"systems that periodically provide them with recommendations of recently published papers that are similar to…
Improving Language Models with Advantage-based Offline Policy Gradients
Language Models (LMs) achieve substantial language capabilities when finetuned using Reinforcement Learning with Human Feedback (RLHF). However, RLHF is an unstable and data-hungry process that…
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
Recent works have showcased the ability of LLMs to embody diverse personas in their responses, exemplified by prompts like 'You are Yoda. Explain the Theory of Relativity.' While this ability allows…
BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is…