Search Results for author:
Found 24 papers, 13 papers with code
Distilling Text Style Transfer With Self-Explanation From LLMs
Text Style Transfer (TST) seeks to alter the style of text while retaining its core content.
Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision
In this paper, to avoid the expensive effort of human annotation on the verifier training data, we introduce Model-induced Process Supervision (MiPS), a novel method for automating data curation.
Enabling Language Models to Implicitly Learn Self-Improvement
Specifically, we reformulate the training objective of reinforcement learning from human feedback (RLHF) -- instead of maximizing response quality for a given input, we maximize the quality gap of the response conditioned on a reference response.
Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models
Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost.
Token Imbalance Adaptation for Radiology Report Generation
Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens.
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models).
Large Language Models Can Self-Improve
We show that our approach improves the general reasoning ability of a 540B-parameter LLM (74. 4%->82. 1% on GSM8K, 78. 2%->83. 0% on DROP, 90. 0%->94. 4% on OpenBookQA, and 63. 4%->67. 9% on ANLI-A3) and achieves state-of-the-art-level performance, without any ground truth label.
Ranked #1 on
Question Answering
on DROP
Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification
Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations from the source domain and unlabeled data from the target domain.
Token Dropping for Efficient BERT Pretraining
Transformer-based models generally allocate the same amount of computation for each token in a given sequence.
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance
In this paper, we study contrastive learning from an optimization perspective, aiming to analyze and address a fundamental issue of existing contrastive learning methods that either rely on a large batch size or a large dictionary of feature vectors.
A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation
Rating prediction is a core problem in recommender systems to quantify user's preferences towards items, however, rating imbalance naturally roots in real-world user ratings that cause biased predictions and lead to poor performance on tail ratings.
TADO: Time-varying Attention with Dual-Optimizer Model
As the first attempt in this field to address this problem, we propose a flexible dual-optimizer model to gain robustness from both regression loss and classification loss.
Knowledge Embedding Based Graph Convolutional Network
Recently, a considerable literature has grown up around the theme of Graph Convolutional Network (GCN).
Graph-Revised Convolutional Network
Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications.
Active Learning for Graph Neural Networks via Node Feature Propagation
Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data.
Active Learning Graph Neural Networks via Node Feature Propagation
Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data.
StoryGAN: A Sequential Conditional GAN for Story Visualization
We therefore propose a new story-to-image-sequence generation model, StoryGAN, based on the sequential conditional GAN framework.
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning
Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences.
Unsupervised Cross-lingual Transfer of Word Embedding Spaces
Supervised methods for this problem rely on the availability of cross-lingual supervision, either using parallel corpora or bilingual lexicons as the labeled data for training, which may not be available for many low resource languages.
Contextual Encoding for Translation Quality Estimation
In this paper, propose a method to effectively encode the local and global contextual information for each target word using a three-part neural network approach.
Analogical Inference for Multi-Relational Embeddings
Large-scale multi-relational embedding refers to the task of learning the latent representations for entities and relations in large knowledge graphs.
Ranked #24 on
Link Prediction
on WN18
Review Networks for Caption Generation
We propose a novel extension of the encoder-decoder framework, called a review network.
Computational Protein Design Using AND/OR Branch-and-Bound Search
The computation of the global minimum energy conformation (GMEC) is an important and challenging topic in structure-based computational protein design.
