Search Results for author:
Found 12 papers, 9 papers with code
Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Crucially, these improvements require no fine-tuning on these tasks.
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages.
Class Incremental Learning via Likelihood Ratio Based Task Prediction
An emerging theory-guided approach (called TIL+OOD) is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with catastrophic forgetting.
Class-Incremental Learning based on Label Generation
Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF).
ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
We take the first step by focusing on event commonsense that considers events and their relations, and is crucial in both dialogues and general commonsense reasoning.
Continual Pre-training of Language Models
A novel proxy is also proposed to preserve the general knowledge in the original LM.
Ranked #1 on
Continual Pretraining
on ACL-ARC
Adapting a Language Model While Preserving its General Knowledge
This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge.
LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training
But current approaches to rich-number tasks with transformer-based language models abandon or lose some of the numeracy information - e. g., breaking numbers into sub-word tokens - which leads to many number-related errors.
FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information
To assist form designers, in this work we present FormLM to model online forms (by enhancing pre-trained language model with form structural information) and recommend form creation ideas (including question / options recommendations and block type suggestion).
Continual Training of Language Models for Few-Shot Learning
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications.
Ranked #1 on
Continual Pretraining
on AG News
AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks
Tabular data analysis is performed every day across various domains.
Efficient Out-of-Distribution Detection via CVAE data Generation
Recently, contrastive loss with data augmentation and pseudo class creation has been shown to produce markedly better results for out-of-distribution (OOD) detection than previous methods.
