Search Results for author:
Found 17 papers, 11 papers with code
ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Contrastive Framework
Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e. g., English) and non-dominant ones due to the imbalance of training data across languages.
TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
TemporalBench consists of ~10K video question-answer pairs, derived from ~2K high-quality human annotations detailing the temporal dynamics in video clips.
Configurable Foundation Models: Building LLMs from a Modular Perspective
We first formalize modules into emergent bricks - functional neuron partitions that emerge during the pre-training phase, and customized bricks - bricks constructed via additional post-training to improve the capabilities and knowledge of LLMs.
Data Contamination Can Cross Language Barriers
In addition, we discuss the potential utilization of cross-lingual contamination in interpreting LLMs' working mechanisms and in post-training LLMs for enhanced multilingual capabilities.
Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
Controlling the attribute intensity of text generation is crucial across scenarios (e. g., writing conciseness, chatting emotion, and explanation clarity).
Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph
In this paper, we delve into the patent approval pre-diction task and unveil that simple domain-specific graph methods outperform enlarging the model, using the intrinsic dependencies within the patent data.
MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks
We construct the distillation dataset via sampling sentences from language model pre-training datasets (e. g., OpenWebText in our implementation) and prompting an LLM to identify the typed spans of "important information".
MUSER: A Multi-View Similar Case Retrieval Dataset
Furthermore, the case similarities are typically measured solely by the textual semantics of the fact descriptions, which may fail to capture the full complexity of legal cases from the perspective of legal knowledge.
OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding
Event understanding aims at understanding the content and relationship of events within texts, which covers multiple complicated information extraction tasks: event detection, event argument extraction, and event relation extraction.
The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation
In this paper, we check the reliability of EE evaluations and identify three major pitfalls: (1) The data preprocessing discrepancy makes the evaluation results on the same dataset not directly comparable, but the data preprocessing details are not widely noted and specified in papers.
Re-thinking and Re-labeling LIDC-IDRI for Robust Pulmonary Cancer Prediction
The LIDC-IDRI database is the most popular benchmark for lung cancer prediction.
LEVEN: A Large-Scale Chinese Legal Event Detection Dataset
However, existing Legal Event Detection (LED) datasets only concern incomprehensive event types and have limited annotated data, which restricts the development of LED methods and their downstream applications.
Faithful learning with sure data for lung nodule diagnosis
In this study, we construct a sure dataset with pathologically-confirmed labels and propose a collaborative learning framework to facilitate sure nodule classification by integrating unsure data knowledge through nodule segmentation and malignancy score regression.
Relationship between pulmonary nodule malignancy and surrounding pleurae, airways and vessels: a quantitative study using the public LIDC-IDRI dataset
The correlation between nodules and the counting number of airways and vessels that contact or project towards nodules are respectively (OR=22. 96, \chi^2=105. 04) and (OR=7. 06, \chi^2=290. 11).
Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT
Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background.
Continuous Implicit Authentication for Mobile Devices based on Adaptive Neuro-Fuzzy Inference System
In order to improve mobile security, an adaptive neuro-fuzzy inference system(ANFIS)-based implicit authentication system is proposed in this paper to provide authentication in a continuous and transparent manner. To illustrate the applicability and capability of ANFIS in our implicit authentication system, experiments were conducted on behavioural data collected for up to 12 weeks from different Android users.
Fuzzy Logic-based Implicit Authentication for Mobile Access Control
In order to address the increasing compromise of user privacy on mobile devices, a Fuzzy Logic based implicit authentication scheme is proposed in this paper.
Cryptography and Security
