Mengting Wan
YOU?
Author Swipe
View article: The involvement of m6A RNA methylation in the transgenerational inheritance of hepatotoxicity induced by paternal cadmium exposure
The involvement of m6A RNA methylation in the transgenerational inheritance of hepatotoxicity induced by paternal cadmium exposure Open
Cadmium (Cd), a widespread environmental pollutant, has linked with various adverse health effects. However, the paternally inherited transgenerational effects of cadmium exposure on hepatotoxicity inoffspring and the underlying mechanism …
View article: Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies
Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies Open
Understanding user intents in information access scenarios can help us provide more relevant and personalized search results and recommendations. However, analyzing user intents is not easy, especially for emerging forms of Web search such…
View article: Lipid metabolic reprograming: the unsung hero in breast cancer progression and tumor microenvironment
Lipid metabolic reprograming: the unsung hero in breast cancer progression and tumor microenvironment Open
View article: GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation Open
Large Language Models (LLMs) can enhance their capabilities as AI assistants by integrating external tools, allowing them to access a wider range of information. While recent LLMs are typically fine-tuned with tool usage examples during su…
View article: GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation Open
View article: Group Preference Alignment: Customizing LLM Responses from In-Situ Conversations Only When Needed
Group Preference Alignment: Customizing LLM Responses from In-Situ Conversations Only When Needed Open
View article: Teaching Language Models To Gather Information Proactively
Teaching Language Models To Gather Information Proactively Open
View article: Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface Open
Agents, as user-centric tools, are increasingly deployed for human task delegation, assisting with a broad spectrum of requests by generating thoughts, engaging with user proxies, and producing action plans. However, agents based on large …
View article: Recent Development of Functional Bio-Based Epoxy Resins
Recent Development of Functional Bio-Based Epoxy Resins Open
The development of epoxy resins is mainly dependent on non-renewable petroleum resources, commonly diglycidyl ether bisphenol A (DGEBA)-type epoxy monomers. Most raw materials of these thermoset resins are toxic to the health of human bein…
View article: WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback Open
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their resource…
View article: TnT-LLM: Text Mining at Scale with Large Language Models
TnT-LLM: Text Mining at Scale with Large Language Models Open
Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application. However, most existing methods for producing label taxo…
View article: LCP1 correlates with immune infiltration: a prognostic marker for triple-negative breast cancer
LCP1 correlates with immune infiltration: a prognostic marker for triple-negative breast cancer Open
Objective Triple-Negative Breast Cancer (TNBC) is known for its aggressiveness and treatment challenges due to the absence of ER, PR, and HER2 receptors. Our work emphasizes the prognostic value of LCP1 (Lymphocyte cytosolic protein 1), wh…
View article: Review of Recyclable Bio-based Epoxy Resins with Dynamic Chemical Bonds
Review of Recyclable Bio-based Epoxy Resins with Dynamic Chemical Bonds Open
Epoxy thermosetting resins are usually reliant on fossil fuel-based resources, commonly diglycidyl ether bisphenol A (DGEBA) type epoxy monomers. Most raw materials of these thermoset resin are toxic to the health of human, and their etern…
View article: Corporate Communication Companion (CCC): An LLM-empowered Writing Assistant for Workplace Social Media
Corporate Communication Companion (CCC): An LLM-empowered Writing Assistant for Workplace Social Media Open
Workplace social media platforms enable employees to cultivate their professional image and connect with colleagues in a semi-formal environment. While semi-formal corporate communication poses a unique set of challenges, large language mo…
View article: LCP1 is a potential prognostic biomarker and correlates with immune infiltration in triple negative breast cancer
LCP1 is a potential prognostic biomarker and correlates with immune infiltration in triple negative breast cancer Open
Objective Triple-Negative Breast Cancer (TNBC), known for its aggressiveness and treatment challenges due to the absence of ER, PR, and HER2 receptors, is the focus of this study. The research emphasizes the need for new biomarkers like LC…
View article: The Use of Generative Search Engines for Knowledge Work and Complex Tasks
The Use of Generative Search Engines for Knowledge Work and Complex Tasks Open
Until recently, search engines were the predominant method for people to access online information. The recent emergence of large language models (LLMs) has given machines new capabilities such as the ability to generate new digital artifa…
View article: Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models Open
Accurate and interpretable user satisfaction estimation (USE) is critical for understanding, evaluating, and continuously improving conversational systems. Users express their satisfaction or dissatisfaction with diverse conversational pat…
View article: TnT-LLM: Text Mining at Scale with Large Language Models
TnT-LLM: Text Mining at Scale with Large Language Models Open
Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application. However, most existing methods for producing label taxo…
View article: Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers
Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers Open
Powerful large language models have facilitated the development of writing assistants that promise to significantly improve the quality and efficiency of composition and communication. However, a barrier to effective assistance is the lack…
View article: Revisit to the yield ratio of triton and $^3$He as an indicator of neutron-rich neck emission
Revisit to the yield ratio of triton and $^3$He as an indicator of neutron-rich neck emission Open
The neutron rich neck zone created in heavy ion reaction is experimentally probed by the production of the $A=3$ isobars. The energy spectra and angular distributions of triton and $^3$He are measured with the CSHINE detector in $^{86}$Kr …
View article: S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs Open
The traditional Dialogue State Tracking (DST) problem aims to track user preferences and intents in user-agent conversations. While sufficient for task-oriented dialogue systems supporting narrow domain applications, the advent of Large La…
View article: Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies
Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies Open
Log data can reveal valuable information about how users interact with Web search services, what they want, and how satisfied they are. However, analyzing user intents in log data is not easy, especially for emerging forms of Web search su…
View article: Learning Causal Effects on Hypergraphs (Extended Abstract)
Learning Causal Effects on Hypergraphs (Extended Abstract) Open
Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes. Different from most existing studies which leverage statistical dependencies, we stud…
View article: Large-Scale Analysis of New Employee Network Dynamics
Large-Scale Analysis of New Employee Network Dynamics Open
The COVID-19 pandemic has accelerated digital transformations across\nindustries, but also introduced new challenges into workplaces, including the\ndifficulties of effectively socializing with colleagues when working remotely.\nThis chall…
View article: Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates
Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates Open
With information systems becoming larger scale, recommendation systems are a topic of growing interest in machine learning research and industry. Even though progress on improving model design has been rapid in research, we argue that many…
View article: Observing the Ping-pong Modality of Isospin Degree of Freedom in Cluster Emission from Heavy Ion Reactions
Observing the Ping-pong Modality of Isospin Degree of Freedom in Cluster Emission from Heavy Ion Reactions Open
Two-body correlations of the isotope-resolved light and heavy clusters are measured in $^{86}$Kr+$^{\rm 208}$Pb reactions at 25 MeV/u. The yield and kinetic variables of the $A=3$ isobars, triton and $^3$He, are analyzed in coincidence wit…
View article: Learning Causal Effects on Hypergraphs
Learning Causal Effects on Hypergraphs Open
Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes. Different from most existing studies which leverage statistical dependencies, we stud…
View article: Learning Causal Effects on Hypergraphs
Learning Causal Effects on Hypergraphs Open
Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes. Different from most existing studies which leverage statistical dependencies, we stud…
View article: Learning Fair Node Representations with Graph Counterfactual Fairness
Learning Fair Node Representations with Graph Counterfactual Fairness Open
Fair machine learning aims to mitigate the biases of model predictions\nagainst certain subpopulations regarding sensitive attributes such as race and\ngender. Among the many existing fairness notions, counterfactual fairness\nmeasures the…
View article: Tuberous sclerosis complex-lymphangioleiomyomatosis involving several visceral organs: A case report
Tuberous sclerosis complex-lymphangioleiomyomatosis involving several visceral organs: A case report Open
We highlight a rare case of TSC-LAM and the first report of a mediastinum lymphangioleiomyoma associated with TSC-LAM.