Search Results for author:
Found 19 papers, 8 papers with code
Unveiling the Generalization Power of Fine-Tuned Large Language Models
While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their counterparts without fine-tuning.
A Thorough Examination of Decoding Methods in the Era of LLMs
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers.
Hyperedge Interaction-aware Hypergraph Neural Network
In this paper, we propose HeIHNN, a hyperedge interaction-aware hypergraph neural network, which captures the interactions among hyperedges during the convolution process and introduce a novel mechanism to enhance information flow between hyperedges and nodes.
HC-Ref: Hierarchical Constrained Refinement for Robust Adversarial Training of GNNs
Recent studies have shown that attackers can catastrophically reduce the performance of GNNs by maliciously modifying the graph structure or node features on the graph.
A Frustratingly Simple Decoding Method for Neural Text Generation
We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation.
Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) even when trained without parallel data.
Being Automated or Not? Risk Identification of Occupations with Graph Neural Networks
In this paper, we study the automation risk of occupations by performing a classification task between automated and non-automated occupations.
Mitigating the Performance Sacrifice in DP-Satisfied Federated Settings through Graph Contrastive Learning
Currently, graph learning models are indispensable tools to help researchers explore graph-structured data.
Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning
In this paper, we propose a novel method to utilize \textbf{C}ounterfactual mechanism to generate artificial hard negative samples for \textbf{G}raph \textbf{C}ontrastive learning, namely \textbf{CGC}, which has a different perspective compared to those sampling-based strategies.
COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
In this work, we propose COSPLAY(COncept Set guided PersonaLized dialogue generation Across both partY personas) that considers both parties as a "team": expressing self-persona while keeping curiosity toward the partner, leading responses around mutual personas, and finding the common ground.
Parameter-Efficient Tuning by Manipulating Hidden States of Pretrained Language Models For Classification Tasks
Continuous prompt tuning which prepends a few trainable vectors to the embeddings of input is one of these methods and has drawn much attention due to its effectiveness and efficiency.
Graph Masked Autoencoders with Transformers
In this paper, we propose Graph Masked Autoencoders (GMAEs), a self-supervised transformer-based model for learning graph representations.
Dual Space Graph Contrastive Learning
In addition, we conduct extensive experiments to analyze the impact of different graph encoders on DSGC, giving insights about how to better leverage the advantages of contrastive learning between different spaces.
Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation
They utilize simple and fixed schemes, like neighborhood information aggregation or mathematical calculation of vectors, to fuse the embeddings of different user behaviors to obtain a unified embedding to represent a user's behavioral patterns which will be used in downstream recommendation tasks.
Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence.
Sentence Structure and Word Relationship Modeling for Emphasis Selection
In this paper, we propose a new framework that considers sentence structure via a sentence structure graph and word relationship via a word similarity graph.
Semantic Segmentation by Improved Generative Adversarial Networks
Besides, the adversarial loss aggressively encourages the output image to be close to the distribution of the ground truth.
A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
To address this, we propose a neural topical expansion framework, namely Persona Exploration and Exploitation (PEE), which is able to extend the predefined user persona description with semantically correlated content before utilizing them to generate dialogue responses.
