Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Anthropomorphization of AI: Opportunities and Risks
Anthropomorphization is the tendency to attribute human-like traits to non-human entities. It is prevalent in many social contexts -- children anthropomorphize toys, adults do so with brands, and it…
CSTS: Conditional Semantic Textual Similarity
Semantic textual similarity (STS) has been a cornerstone task in NLP that measures the degree of similarity between a pair of sentences, with applications in information retrieval, question…
OpenPI2.0: An Improved Dataset for Entity Tracking in Texts
Representing texts as information about entities has long been deemed effective in event reasoning. We propose OpenPI2.0, an improved dataset for tracking entity states in procedural texts.…
Improving Language Models via Plug-and-Play Retrieval Feedback
Large language models (LLMs) exhibit remarkable performance across various NLP tasks. However, they often generate incorrect or hallucinated information, which hinders their practical applicability…
Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
We study whether multiple large language models (LLMs) can autonomously improve each other in a negotiation game by playing, reflecting, and criticizing. We are interested in this question because…
Can AI language models replace human participants?
Recent work suggests that language models such as GPT can make human-like judgments across a number of domains. We explore whether and when language models might replace human participants in…
Complexity-Based Prompting for Multi-Step Reasoning
We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences…
Decomposed Prompting: A Modular Approach for Solving Complex Tasks
Few-shot prompting is a surprisingly powerful way to use Large Language Models (LLMs) to solve various tasks. However, this approach struggles as the task complexity increases or when the individual…
Toxicity in ChatGPT: Analyzing Persona-assigned Language Models
Large language models (LLMs) have shown incredible capabilities and transcended the natural language processing (NLP) community, with adoption throughout many services like healthcare, therapy,…
The Parallelism Tradeoff: Limitations of Log-Precision Transformers
Abstract Despite their omnipresence in modern NLP, characterizing the computational power of transformer neural nets remains an interesting open question. We prove that transformers whose arithmetic…