Search Results for author:
Found 48 papers, 18 papers with code
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods.
Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content.
MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
We find that directly using smaller pre-trained models and applying magnitude-based pruning on CLIP models leads to inflexibility and inferior performance.
Can LLM Substitute Human Labeling? A Case Study of Fine-grained Chinese Address Entity Recognition Dataset for UAV Delivery
We present CNER-UAV, a fine-grained \textbf{C}hinese \textbf{N}ame \textbf{E}ntity \textbf{R}ecognition dataset specifically designed for the task of address resolution in \textbf{U}nmanned \textbf{A}erial \textbf{V}ehicle delivery systems.
Understanding and Patching Compositional Reasoning in LLMs
LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving.
Improved Quantization Strategies for Managing Heavy-tailed Gradients in Distributed Learning
We consider a general family of heavy-tail gradients that follow a power-law distribution, we aim to minimize the error resulting from quantization, thereby determining optimal values for two critical parameters: the truncation threshold and the quantization density.
Truncated Non-Uniform Quantization for Distributed SGD
To address the communication bottleneck challenge in distributed learning, our work introduces a novel two-stage quantization strategy designed to enhance the communication efficiency of distributed Stochastic Gradient Descent (SGD).
PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
LLMs are prompted to generate extensive content in response to these meta-questions.
Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation
Conventional recommendation methods have achieved notable advancements by harnessing collaborative or sequential information from user behavior.
3D Shape Completion on Unseen Categories:A Weakly-supervised Approach
Specifically, we construct a prior bank consisting of representative shapes from the seen categories.
RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation
Large Language Models (LLMs) have demonstrated remarkable capabilities and have been extensively deployed across various domains, including recommender systems.
CLOMO: Counterfactual Logical Modification with Large Language Models
In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs).
Fine-grained Conversational Decoding via Isotropic and Proximal Search
General-purpose text decoding approaches are usually adopted for dialogue response generation.
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
In this paper, we present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations and, consequently, enhancing their mathematical reasoning abilities.
Ranked #4 on
Math Word Problem Solving
on SVAMP
(using extra training data)
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
We found that its success can be largely attributed to its powerful skills in generating and executing code, evaluating the output of code execution, and rectifying its solution when receiving unreasonable outputs.
Ranked #1 on
Math Word Problem Solving
on MATH
Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts
Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content.
PerFedRec++: Enhancing Personalized Federated Recommendation with Self-Supervised Pre-Training
Each user learns a personalized model by combining the global federated model, the cluster-level federated model, and its own fine-tuned local model.
VCSUM: A Versatile Chinese Meeting Summarization Dataset
Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data.
Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning
Communication efficiency and privacy protection are two critical issues in distributed machine learning.
A Scalable Test Problem Generator for Sequential Transfer Optimization
Lastly, a benchmark suite with 12 STO problems featured by a variety of customized similarity relationships is developed using the proposed generator.
Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement
Subsequently, we propose an objective quality assessment measure that plays a critical role in bridging the gap between visual quality and enhancement.
Adaptive Top-K in SGD for Communication-Efficient Distributed Learning
This paper proposes a novel adaptive Top-K in SGD framework that enables an adaptive degree of sparsification for each gradient descent step to optimize the convergence performance by balancing the trade-off between communication cost and convergence error.
Hiding Images in Deep Probabilistic Models
As an instantiation, we adopt a SinGAN, a pyramid of generative adversarial networks (GANs), to learn the patch distribution of one cover image.
Towards Communication Efficient and Fair Federated Personalized Sequential Recommendation
Federated recommendations leverage the federated learning (FL) techniques to make privacy-preserving recommendations.
HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendations
For example, in a mobile game recommendation, contextual features like locations, battery, and storage levels of mobile devices are frequently drifting over time.
Personalized Federated Recommendation via Joint Representation Learning, User Clustering, and Model Adaptation
In this paper, we propose a Graph Neural Network based Personalized Federated Recommendation (PerFedRec) framework via joint representation learning, user clustering, and model adaptation.
Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models
In this paper, we propose an embedding regularized neural topic model, which applies the specially designed training constraints on word embedding and topic embedding to reduce the optimization space of parameters.
Learning Locality and Isotropy in Dialogue Modeling
Existing dialogue modeling methods have achieved promising performance on various dialogue tasks with the aid of Transformer and the large-scale pre-trained language models.
Zero-shot Cross-lingual Conversational Semantic Role Labeling
While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training.
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings
Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e. g., SimCSE.
Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits
Our bandit learning algorithms are based on epoch-wise sub-optimal arm eliminations at each agent and agents exchange learning knowledge with the server/each other at the end of each epoch.
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding.
Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering
To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e. g., by computing validation error rate) or leverages statistic-based methods (e. g. median and Krum) to identify and remove malicious gradients from Byzantine clients.
DQ-SGD: Dynamic Quantization in SGD for Communication-Efficient Distributed Learning
Gradient quantization is an emerging technique in reducing communication costs in distributed learning.
Domain-Adaptive Pretraining Methods for Dialogue Understanding
Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks.
Conversational Semantic Role Labeling
Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence.
EGFI: Drug-Drug Interaction Extraction and Generation with Fusion of Enriched Entity and Sentence Information
To address such a problem, we propose EGFI for extracting and consolidating drug interactions from large-scale medical literature text data.
DQSGD: DYNAMIC QUANTIZED STOCHASTIC GRADIENT DESCENT FOR COMMUNICATION-EFFICIENT DISTRIBUTED LEARNING
This paper addresses this issue by proposing a novel dynamic quantized SGD (DQSGD) framework, which enables us to optimize the quantization strategy for each gradient descent step by exploring the trade-off between communication cost and modeling error.
Distributed Thompson Sampling
To further improve the performance of distributed Thompson Sampling, we propose a distributed Elimination based Thompson Sampling algorithm that allow the agents to learn collaboratively.
Semantic Role Labeling Guided Multi-turn Dialogue ReWriter
For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance.
Federated Recommendation System via Differential Privacy
In this paper, we are interested in what we term the federated private bandits framework, that combines differential privacy with multi-agent bandit learning.
The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost
Our proposed federated XGBoost algorithm incorporates data aggregation and sparse federated update processes to balance the tradeoff between privacy and learning performance.
Data Encoding for Byzantine-Resilient Distributed Optimization
In this paper, we propose a method based on data encoding and error correction over real numbers to combat adversarial attacks.
Equivariant neural networks and equivarification
We provide a process to modify a neural network to an equivariant one, which we call equivarification.
Regret vs. Bandwidth Trade-off for Recommendation Systems
We consider recommendation systems that need to operate under wireless bandwidth constraints, measured as number of broadcast transmissions, and demonstrate a (tight for some instances) tradeoff between regret and bandwidth for two scenarios: the case of multi-armed bandit with context, and the case where there is a latent structure in the message space that we can exploit to reduce the learning phase.
A Contextual Bandit Approach for Stream-Based Active Learning
The key feature of our algorithm is that in addition to sending a query to an annotator for the ground truth, prior information about the ground truth learned by the learner is sent together, thereby reducing the query cost.
Stream-based Online Active Learning in a Contextual Multi-Armed Bandit Framework
In a stream-based active learning setting, obtaining the ground truth of the reward is costly, and the conventional contextual multi-armed bandit algorithm fails to achieve a sublinear regret due to this cost.
