Search Results for author:
Found 73 papers, 28 papers with code
De-Biased Court's View Generation with Causality
Court{'}s view generation is a novel but essential task for legal AI, aiming at improving the interpretability of judgment prediction results and enabling automatic legal document generation.
LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation
To address these challenges, we introduce LeCoDe, a real-world multi-turn benchmark dataset comprising 3, 696 legal consultation dialogues with 110, 008 dialogue turns, designed to evaluate and improve LLMs' legal consultation capability.
CLaDMoP: Learning Transferrable Models from Successful Clinical Trials via LLMs
To address this limitation, we introduce CLaDMoP, a new pre-training approach for clinical trial outcome prediction, alongside the Successful Clinical Trials dataset(SCT), specifically designed for this task.
AppealCase: A Dataset and Benchmark for Civil Case Appeal Scenarios
Recent advances in LegalAI have primarily focused on individual case judgment analysis, often overlooking the critical appellate process within the judicial system.
KEDRec-LM: A Knowledge-distilled Explainable Drug Recommendation Large Language Model
Drug discovery is a critical task in biomedical natural language processing (NLP), yet explainable drug discovery remains underexplored.
Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning
Large Language Models (LLMs) have achieved impressive results across numerous domains, yet they experience notable deficiencies in legal question-answering tasks.
Auto-Drafting Police Reports from Noisy ASR Outputs: A Trust-Centered LLM Approach
Achieving a delicate balance between fostering trust in law en- forcement and protecting the rights of both officers and civilians continues to emerge as a pressing research and product challenge in the world today.
Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models
Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become essential for tasks such as question answering and content generation.
MEXA-CTP: Mode Experts Cross-Attention for Clinical Trial Outcome Prediction
Clinical trials are the gold standard for assessing the effectiveness and safety of drugs for treating diseases.
FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation Models
In this paper, we investigate a more realistic and critical threat scenario: adversarial attacks intended for opinion manipulation against black-box RAG models, particularly on controversial topics.
ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning
In this work, we focus on the data selection problem for task-specific instruction tuning of LLMs.
Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning
A vast amount of scholarly work is published daily, yet much of it remains inaccessible to the general public due to dense jargon and complex language.
LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model
Graph foundation models (GFMs) have recently gained significant attention.
A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment Analysis
It is observed that whether the user's needs are met often triggers various sentiments, which can be pertinent to the successful estimation of user satisfaction, and vice versa.
LLM Cascade with Multi-Objective Optimal Consideration
Large Language Models (LLMs) have demonstrated exceptional capabilities in understanding and generating natural language.
Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration
Large Language Models (LLMs) could struggle to fully understand legal theories and perform complex legal reasoning tasks.
Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models
Retrieval-Augmented Generation (RAG) is applied to solve hallucination problems and real-time constraints of large language models, but it also induces vulnerabilities against retrieval corruption attacks.
Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning
The integration of generative Large Language Models (LLMs) into various applications, including the legal domain, has been accelerated by their expansive and versatile nature.
Enhance Robustness of Language Models Against Variation Attack through Graph Integration
The widespread use of pre-trained language models (PLMs) in natural language processing (NLP) has greatly improved performance outcomes.
From Model-centered to Human-Centered: Revision Distance as a Metric for Text Evaluation in LLMs-based Applications
Therefore, our study shifts the focus from model-centered to human-centered evaluation in the context of AI-powered writing assistance applications.
Personalized LLM Response Generation with Parameterized Memory Injection
Large Language Models (LLMs) have exhibited remarkable proficiency in comprehending and generating natural language.
Empowering Dual-Level Graph Self-Supervised Pretraining with Motif Discovery
While self-supervised graph pretraining techniques have shown promising results in various domains, their application still experiences challenges of limited topology learning, human knowledge dependency, and incompetent multi-level interactions.
Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph
Heterogeneous graph neural networks have become popular in various domains.
Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration
Precedents are the previous legal cases with similar facts, which are the basis for the judgment of the subsequent case in national legal systems.
Large Language Model Soft Ideologization via AI-Self-Consciousness
Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks.
LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination
We contend that a mere memory module is inadequate and fully training an LLM can be excessively costly.
Community-Based Hierarchical Positive-Unlabeled (PU) Model Fusion for Chronic Disease Prediction
Positive-Unlabeled (PU) Learning is a challenge presented by binary classification problems where there is an abundance of unlabeled data along with a small number of positive data instances, which can be used to address chronic disease screening problem.
I3: Intent-Introspective Retrieval Conditioned on Instructions
Recent studies indicate that dense retrieval models struggle to perform well on a wide variety of retrieval tasks that lack dedicated training data, as different retrieval tasks often entail distinct search intents.
Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document
GOSE initiates by generating preliminary relation predictions on entity pairs extracted from a scanned image of the document.
MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion
As a prominent instance of vandalism edits, Wiki search poisoning for illicit promotion is a cybercrime in which the adversary aims at editing Wiki articles to promote illicit businesses through Wiki search results of relevant queries.
Multidimensional Perceptron for Efficient and Explainable Long Text Classification
Because of the inevitable cost and complexity of transformer and pre-trained models, efficiency concerns are raised for long text classification.
Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization
Though effective, prompt tuning under few-shot settings on the one hand heavily relies on a good initialization of soft prompts.
AI vs. Human -- Differentiation Analysis of Scientific Content Generation
We find that there exists a "writing style" gap between AI-generated scientific text and human-written scientific text.
Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models
In this study, we propose an imitation adversarial attack on black-box neural passage ranking models.
Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning
Motivated by the industry practice of labeling data, we propose an innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL's potential superiority and achieve mutual enhancement of AL and SSL, i. e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL.
Dialogue Inspectional Summarization with Factual Inconsistency Awareness
Dialogue summarization has been extensively studied and applied, where the prior works mainly focused on exploring superior model structures to align the input dialogue and the output summary.
A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis
Chatbot is increasingly thriving in different domains, however, because of unexpected discourse complexity and training data sparseness, its potential distrust hatches vital apprehension.
A Neural Conversation Generation Model via Equivalent Shared Memory Investigation
Nevertheless, few works utilized the knowledge extracted from similar conversations for utterance generation.
RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy
In the field of dialogue summarization, due to the lack of training data, it is often difficult for supervised summary generation methods to learn vital information from dialogue context with limited data.
Legal Judgment Prediction with Multi-Stage CaseRepresentation Learning in the Real Court Setting
Legal judgment prediction(LJP) is an essential task for legal AI.
Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning
Relational fact extraction aims to extract semantic triplets from unstructured text.
Ranked #6 on
Relation Extraction
on NYT
Cross-Domain Contract Element Extraction with a Bi-directional Feedback Clause-Element Relation Network
First, contract elements are far more fine-grained than named entities, which hinders the transfer of extractors.
Cross-Domain Named Entity Recognition
Graph Neural Network
+5
Improving Community Detection Performance in Heterogeneous Music Network by Learning Edge-type Usefulness Distribution
Therefore a heterogeneous network can be converted to a homogeneous one where those conventional methods are eligible to use.
Leveraging Online Shopping Behaviors as a Proxy for Personal Lifestyle Choices: New Insights into Chronic Disease Prevention Literacy
Objective: Ubiquitous internet access is reshaping the way we live, but it is accompanied by unprecedented challenges in preventing chronic diseases that are usually planted by long exposure to unhealthy lifestyles.
Community-based Cyberreading for Information Understanding
Although the content in scientific publications is increasingly challenging, it is necessary to investigate another important problem, that of scientific information understanding.
Biomedical Question Answering: A Survey of Approaches and Challenges
Automatic Question Answering (QA) has been successfully applied in various domains such as search engines and chatbots.
Chronological Citation Recommendation with Time Preference
Citation recommendation is an important task to assist scholars in finding candidate literature to cite.
Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling
In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics.
Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff
Is chatbot able to completely replace the human agent?
Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue
As an important research topic, customer service dialogue generation tends to generate generic seller responses by leveraging current dialogue information.
Cross Copy Network for Dialogue Generation
In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e. g., LSTM+attention, Pointer Generator Networks, and Transformer) to enhance dialogue content generation.
Predicting Clinical Trial Results by Implicit Evidence Integration
In the CTRP framework, a model takes a PICO-formatted clinical trial proposal with its background as input and predicts the result, i. e. how the Intervention group compares with the Comparison group in terms of the measured Outcome in the studied Population.
Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning
In this paper, our model, Pairwise Cross-graph Community Detection (PCCD), is proposed to cope with the sparse graph problem by involving external graph knowledge to learn user pairwise community closeness instead of detecting direct communities.
Efficient Personalized Community Detection via Genetic Evolution
Personalized community detection aims to generate communities associated with user need on graphs, which benefits many downstream tasks such as node recommendation and link prediction for users, etc.
Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning
We propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task.
Community-Based Data Integration of Course and Job Data in Support of Personalized Career-Education Recommendations
How does your education impact your professional career?
Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
We manually collect a new and high-quality paired dataset, where each pair contains an unordered product attribute set in the source language and an informative product description in the target language.
Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning
Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc.
Read Beyond the Lines: Understanding the Implied Textual Meaning via a Skim and Intensive Reading Model
The nonliteral interpretation of a text is hard to be understood by machine models due to its high context-sensitivity and heavy usage of figurative language.
Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning
Customers ask questions and customer service staffs answer their questions, which is the basic service model via multi-turn customer service (CS) dialogues on E-commerce platforms.
Uncover Sexual Harassment Patterns from Personal Stories by Joint Key Element Extraction and Categorization
Sexual harassment occurred in a variety of situations, and categorization of the stories and extraction of their key elements will provide great help for the related parties to understand and address sexual harassment.
Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning
This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC.
Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning
Aspect category detection is an essential task for sentiment analysis and opinion mining.
Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation
The VFGE can learn both the graph embeddings of the Chinese characters (local) and the latent variation families (global).
Ranked #1 on
Chinese Spam Detection
on SMS
AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising.
Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network
This paper extends the research to interactive reviews and proposes a new research task, namely Aspect Sentiment Classification towards Question-Answering (ASC-QA), for real-world applications.
Neural Related Work Summarization with a Joint Context-driven Attention Mechanism
Conventional solutions to automatic related work summarization rely heavily on human-engineered features.
Cross-language Citation Recommendation via Hierarchical Representation Learning on Heterogeneous Graph
While the volume of scholarly publications has increased at a frenetic pace, accessing and consuming the useful candidate papers, in very large digital libraries, is becoming an essential and challenging task for scholars.
Sentiment Classification towards Question-Answering with Hierarchical Matching Network
On the basis, we propose a three-stage hierarchical matching network to explore deep sentiment information in a QA text pair.
edge2vec: Representation learning using edge semantics for biomedical knowledge discovery
We propose this method for its added value relative to existing graph analytical methodology, and in the real world context of biomedical knowledge discovery applicability.
One vs. Many QA Matching with both Word-level and Sentence-level Attention Network
Question-Answer (QA) matching is a fundamental task in the Natural Language Processing community.
