Search Results for author:
Found 7 papers, 4 papers with code
Getting aligned on representational alignment
Finally, we lay out open problems in representational alignment where progress can benefit all three of these fields.
Set Learning for Accurate and Calibrated Models
Model overconfidence and poor calibration are common in machine learning and difficult to account for when applying standard empirical risk minimization.
Human alignment of neural network representations
Linear transformations of neural network representations learned from behavioral responses from one dataset substantially improve alignment with human similarity judgments on the other two datasets.
VICE: Variational Interpretable Concept Embeddings
This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task.
Unsupervised Evaluation for Question Answering with Transformers
We observe a consistent pattern in the answer representations, which we show can be used to automatically evaluate whether or not a predicted answer span is correct.
Human brain activity for machine attention
Cognitively inspired NLP leverages human-derived data to teach machines about language processing mechanisms.
Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity
Hence, to answer these subjective questions, a learner must extract opinions and process sentiment for various domains, and additionally, align the knowledge extracted from a paragraph with the natural language utterances in the corresponding question, which together enhance the difficulty of a QA task.
