research
∙
07/31/2023
Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?
Coaxing out desired behavior from pretrained models, while avoiding unde...
share
research
∙
10/14/2021
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
The common practice for training commonsense models has gone from-human-...
research
∙
09/28/2021
Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics
Neural sequence models trained with maximum likelihood estimation have l...
research
∙
04/16/2021
Surface Form Competition: Why the Highest Probability Answer Isn't Always Right
Large language models have shown promising results in zero-shot settings...
research
∙
11/29/2020
Srift: Swift and Thrift Cloud-Based Distributed Training
Cost-efficiency and training time are primary concerns in cloud-based di...
research
∙
10/24/2020
NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
Conditional text generation often requires lexical constraints, i.e., wh...
research
∙
10/16/2020
Reflective Decoding: Unsupervised Paraphrasing and Abductive Reasoning
Pretrained Language Models (LMs) generate text with remarkable quality, ...
research
∙
10/12/2020
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
Abductive and counterfactual reasoning, core abilities of everyday human...
research
∙
09/21/2020
Adjusting for Confounders with Text: Challenges and an Empirical Evaluation Framework for Causal Inference
Leveraging text, such as social media posts, for causal inferences requi...
research
∙
04/11/2020
Unsupervised Commonsense Question Answering with Self-Talk
Natural language understanding involves reading between the lines with i...
research
∙
09/16/2019