Search Results for author:
Found 12 papers, 2 papers with code
DeAL: Decoding-time Alignment for Large Language Models
Current work focuses on alignment at model training time, through techniques such as Reinforcement Learning with Human Feedback (RLHF).
Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion
When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors.
Backward Compatibility During Data Updates by Weight Interpolation
This method interpolates between the weights of the old and new model and we show in extensive experiments that it reduces negative flips without sacrificing the improved accuracy of the new model.
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
First, we measure and analyze model update regression in different model update settings.
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.
Efficient Domain Adaptation of Language Models via Adaptive Tokenization
While adaptive tokenization incurs a 6% increase in model parameters in our experimentation, due to the introduction of 10k new domain-specific tokens, our approach, using 64 vCPUs, is 72x faster than further pretraining the language model on domain-specific corpora on 8 TPUs.
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Behavior of deep neural networks can be inconsistent between different versions.
Context Analysis for Pre-trained Masked Language Models
Pre-trained language models that learn contextualized word representations from a large un-annotated corpus have become a standard component for many state-of-the-art NLP systems.
Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections
Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point.
Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation
Hierarchical neural networks are often used to model inherent structures within dialogues.
Attribute-aware Collaborative Filtering: Survey and Classification
Attribute-aware CF models aims at rating prediction given not only the historical rating from users to items, but also the information associated with users (e. g. age), items (e. g. price), or even ratings (e. g. rating time).
PRUNE: Preserving Proximity and Global Ranking for Network Embedding
We investigate an unsupervised generative approach for network embedding.
