Search Results for author:
Found 41 papers, 24 papers with code
A Structure-Aware Argument Encoder for Literature Discourse Analysis
Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.
PathQG: Neural Question Generation from Facts
Human evaluation also proves that our model is able to generate relevant and informative questions.
Analytical Reasoning of Text
In this paper, we study the challenge of analytical reasoning of text and collect a new dataset consisting of questions from the Law School Admission Test from 1991 to 2016.
ALaRM: Align Language Models via Hierarchical Rewards Modeling
We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences.
Aligning Large Language Models to a Domain-specific Graph Database
Graph Databases (Graph DB) are widely applied in various fields, including finance, social networks, and medicine.
Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation
Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, data noise and probing their problem-solving sub-abilities.
Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
Our analysis of GPT-series models over a rule subset reveals significant gaps in LLMs' logic understanding compared to human performance, especially in compositional and structural complex rules with certain bias patterns.
AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis
To simulate the procedure, we collect high-quality medical records to create patient, examiner, and medical director agents.
Content-Conditioned Generation of Stylized Free hand Sketches
We explore the performance of the model, including using styles randomly sampled from a prior normal distribution to generate images with various free-hand sketching styles, disentangling the painters' styles from known free-hand sketches to generate images with specific styles, and generating images of unknown classes that are not in the training set.
Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion Approach
Automated conversion methods are essential to overcome manual conversion challenges.
Diff-Oracle: Diffusion Model for Oracle Character Generation with Controllable Styles and Contents
To train Diff-Oracle effectively, we propose to obtain pixel-level paired oracle character images (i. e., style and content images) by a pre-trained image-to-image translation model.
Enhance Sketch Recognition's Explainability via Semantic Component-Level Parsing
Humans can recognize varied sketches of a category easily by identifying the concurrence and layout of the intrinsic semantic components of the category, since humans draw free-hand sketches based a common consensus that which types of semantic components constitute each sketch category.
Sketch Input Method Editor: A Comprehensive Dataset and Methodology for Systematic Input Recognition
With the recent surge in the use of touchscreen devices, free-hand sketching has emerged as a promising modality for human-computer interaction.
In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
We further use the data generated by LINK to construct a dataset Logic-Induced-Long-Tail (LINT) that can be used to evaluate downstream models on the long-tail distribution; LINT contains 108K knowledge statements spanning four domains.
DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning
We propose Multiple Experts Fine-tuning Framework to build a financial large language model (LLM), DISC-FinLLM.
DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.
A Dynamic Equivalent Energy Storage Model of Natural Gas Networks for Joint Optimal Dispatch of Electricity-Gas Systems
The development of energy conversion techniques enhances the coupling between the gas network and power system.
Task-Agnostic Structured Pruning of Speech Representation Models
Self-supervised pre-trained models such as Wav2vec2, Hubert, and WavLM have been shown to significantly improve many speech tasks.
DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model
Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisite for their industrial application.
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs
The results demonstrate the effectiveness of our method on logical reasoning over KGs in both inductive and transductive settings.
MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection
Event detection (ED) is aimed to identify the key trigger words in unstructured text and predict the event types accordingly.
Deep Reinforcement Learning Based Vehicle Selection for Asynchronous Federated Learning Enabled Vehicular Edge Computing
Furthermore, as vehicles have different local training time due to various sizes of local data and their different computing capabilities, asynchronous federated learning (AFL) is employed to facilitate the RSU to update the global model immediately after receiving a local model to reduce the aggregation delay.
Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning
Recent pre-trained language models (PLMs) equipped with foundation reasoning skills have shown remarkable performance on downstream complex tasks.
Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result.
Asynchronous Federated Learning for Edge-assisted Vehicular Networks
For the traditional federated learning (FL), vehicles train the data locally to obtain a local model and then upload the local model to the RSU to update the global model, thus the data privacy can be protected through sharing model parameters instead of data.
Multi-parametric Analysis for Mixed Integer Linear Programming: An Application to Transmission Planning and Congestion Control
Finally, the amount of capacity upgrade will be chosen by balancing the cost-reduction rate of the objective function on parameters and the cost of the line upgrade.
Diverse Dance Synthesis via Keyframes with Transformer Controllers
The video and qualitative experimental results demonstrate that the complex motion sequences generated by our algorithm can achieve diverse and smooth motion transitions between keyframes, even for long-term synthesis.
A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training
These two steps are iteratively performed in our framework for continuous learning.
Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering
The results demonstrate significant performance reduction on both answer and supporting facts prediction, verifying the effectiveness of our reasoning chain based attack method for multi-hop reasoning models and the vulnerability of them.
Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval
Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image.
Fine-Grained Element Identification in Complaint Text of Internet Fraud
Existing system dealing with online complaint provides a final decision without explanations.
From LSAT: The Progress and Challenges of Complex Reasoning
Complex reasoning aims to draw a correct inference based on complex rules.
TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning
Considering that theme concepts can be learned from both images and captions, we propose two settings for their representations learning based on TTN.
Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text
Logical reasoning of text requires understanding critical logical information in the text and performing inference over them.
Ranked #7 on
Reading Comprehension
on ReClor
AR-LSAT: Investigating Analytical Reasoning of Text
Analytical reasoning is an essential and challenging task that requires a system to analyze a scenario involving a set of particular circumstances and perform reasoning over it to make conclusions.
Mask Attention Networks: Rethinking and Strengthen Transformer
We therefore introduce a new layer named dynamic mask attention network (DMAN) with a learnable mask matrix which is able to model localness adaptively.
Ranked #11 on
Machine Translation
on WMT2014 English-German
An Enhanced Knowledge Injection Model for Commonsense Generation
Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts.
Denoising Auto-encoding Priors in Undecimated Wavelet Domain for MR Image Reconstruction
At the stage of prior learning, transformed feature images obtained by undecimated wavelet transform are stacked as an input of denoising autoencoder network (DAE).
Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning
Existing research usually employs the architecture of CNN-RNN that views the generation as a sequential decision-making process and the entire dataset vocabulary is used as decoding space.
A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators
Visual Question Generation (VQG) aims to ask natural questions about an image automatically.
