Search Results for author:
Found 25 papers, 15 papers with code
Graph Foundation Models: A Comprehensive Survey
Positioned at the intersection of graph learning and general-purpose AI, GFMs are poised to become foundational infrastructure for open-ended reasoning over structured data.
Can Large Language Models Understand Preferences in Personalized Recommendation?
To address this, we introduce PerRecBench, disassociating the evaluation from these two factors and assessing recommendation techniques on capturing the personal preferences in a grouped ranking manner.
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and ethical concerns.
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems.
CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
Taxonomies play a crucial role in various applications by providing a structural representation of knowledge.
A Psychology-based Unified Dynamic Framework for Curriculum Learning
Leveraging IRT, we propose a Dynamic Data Selection via Model Ability Estimation (DDS-MAE) strategy to schedule the appropriate amount of data during model training.
Large Language Models Can Self-Correct with Key Condition Verification
The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify.
ChatEL: Entity Linking with Chatbots
Fortunately, Large Language Models (LLMs) like GPT provide a highly-advanced solution to the problems inherent in EL models, but simply naive prompts to LLMs do not work well.
Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples
Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering.
EntGPT: Linking Generative Large Language Models with Knowledge Bases
Additionally, our instruction tuning method (EntGPT-I) improves micro-F_1 scores by 2. 1% on average in supervised EL tasks and outperforms several baseline models in six Question Answering tasks.
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning
OPPU integrates parametric user knowledge in the personal PEFT parameters with non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts.
When eBPF Meets Machine Learning: On-the-fly OS Kernel Compartmentalization
Compartmentalization effectively prevents initial corruption from turning into a successful attack.
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning.
MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Our approach uniquely considers the various annotation formats as different "views" and leverages them in training the model.
Automatic Controllable Product Copywriting for E-Commerce
Automatic product description generation for e-commerce has witnessed significant advancement in the past decade.
Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering.
Traceability Transformed: Generating moreAccurate Links with Pre-Trained BERT Models
In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts.
Transfer Learning
Software Engineering
Validating Label Consistency in NER Data Annotation
It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation.
Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER
The training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small labelled data.
Technical Question Answering across Tasks and Domains
In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains.
A Technical Question Answering System with Transfer Learning
In recent years, the need for community technical question-answering sites has increased significantly.
Crossing Variational Autoencoders for Answer Retrieval
Existing methods learned semantic representations with dual encoders or dual variational auto-encoders.
Enhancing Factual Consistency of Abstractive Summarization
Automatic abstractive summaries are found to often distort or fabricate facts in the article.
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method
On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts.
