Search Results for author:
Found 6 papers, 2 papers with code
Generative Calibration for In-context Learning
In this paper, we for the first time theoretically and empirically identify that such a paradox is mainly due to the label shift of the in-context model to the data distribution, in which LLMs shift the label marginal $p(y)$ while having a good label conditional $p(x|y)$.
Interpreting Sentiment Composition with Latent Semantic Tree
As the key to sentiment analysis, sentiment composition considers the classification of a constituent via classifications of its contained sub-constituents and rules operated on them.
Unsupervised Text Style Transfer with Deep Generative Models
We present a general framework for unsupervised text style transfer with deep generative models.
Logic Traps in Evaluating Attribution Scores
Meanwhile, since the reasoning process of deep models is inaccessible, researchers design various evaluation methods to demonstrate their arguments.
Alignment Rationale for Natural Language Inference
Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors.
MIE: A Medical Information Extractor towards Medical Dialogues
Electronic Medical Records (EMRs) have become key components of modern medical care systems.
