Large language models (LLMs) are increasingly adopted for a variety of t...
Large language models (LLMs) are increasingly adopted for knowledge-inte...
Existing work on controlled text generation (CTG) assumes a control inte...
The finetuning of pretrained transformer-based language generation model...
Latent-space interpolation is commonly used to demonstrate the generaliz...
Prompt-based knowledge probing for 1-hop relations has been used to meas...
In this work, we explore joint energy-based model (EBM) training during ...
This work studies the widely adopted ancestral sampling algorithms for
a...
Knowledge graphs (KGs) are relevant to many NLP tasks, but building a
re...
In this work, we study how the large-scale pretrain-finetune framework
c...
We provide a theoretical explanation for the fast convergence of gradien...
The exposure bias problem refers to the training-inference discrepancy c...
Although deep learning models have brought tremendous advancements to th...
In this work, we attempt to answer a critical question: whether there ex...
We propose to train bi-directional neural network language model(NNLM) w...