Yinhong Liu
YOU?
Author Swipe
View article: MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization Open
Multimodal Dialogue Summarization (MDS) is a critical task with wide-ranging applications. To support the development of effective MDS models, robust automatic evaluation methods are essential for reducing both cost and human effort. Howev…
View article: GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking
GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking Open
Large language models (LLMs) are widely used, but they often generate subtle factual errors, especially in long-form text. These errors are fatal in some specialized domains such as medicine. Existing fact-checking with grounding documents…
View article: When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning Open
View article: GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking
GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking Open
Large language models (LLMs) are widely used, but they often generate subtle factual errors, especially in long-form text. These errors are fatal in some specialized domains such as medicine. Existing fact-checking with grounding documents…
View article: MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization Open
View article: Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models Open
Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine logical preference consistenc…
View article: Full-Duplex ISAC-Enabled D2D Underlaid Cellular Networks: Joint Transceiver Beamforming and Power Allocation
Full-Duplex ISAC-Enabled D2D Underlaid Cellular Networks: Joint Transceiver Beamforming and Power Allocation Open
Integrating device-to-device (D2D) communication into cellular networks can significantly reduce the transmission burden on base stations (BSs). Besides, integrated sensing and communication (ISAC) is envisioned as a key feature in future …
View article: MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs Open
Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes. However, evaluating these reasoning abilities has become increasi…
View article: Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments Open
Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language generation quality. In particular, pairwise LLM evaluators, which compare two generated texts and determine …
View article: Alterations in structural integrity of superior longitudinal fasciculus III associated with cognitive performance in cerebral small vessel disease
Alterations in structural integrity of superior longitudinal fasciculus III associated with cognitive performance in cerebral small vessel disease Open
View article: Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators
Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators Open
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent …
View article: TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles
TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles Open
In light of recent advances in large language models (LLMs), the expectations for the next generation of virtual assistants include enhanced naturalness and adaptability across diverse usage scenarios. However, the creation of high-quality…
View article: Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence
Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence Open
Recent large language models (LLMs) have shown remarkable performance in aligning generated text with user intentions across various tasks. When it comes to long-form text generation, there has been a growing interest in generation from a …
View article: Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructions
Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructions Open
Instruction-tuned large language models have shown remarkable performance in aligning generated text with user intentions across various tasks. However, maintaining human-like discourse structure in the generated text remains a challenging…
View article: Prevalence and risk factors for cerebral microbleeds in elderly Chinese patients with arteriosclerotic cardiovascular diseases: A single-center study
Prevalence and risk factors for cerebral microbleeds in elderly Chinese patients with arteriosclerotic cardiovascular diseases: A single-center study Open
View article: Prevalence and Risk Factors for Cerebral Microbleeds in Elderly Chinese Patients with Arteriosclerotic Cardiovascular Diseases:A Single-Center Study
Prevalence and Risk Factors for Cerebral Microbleeds in Elderly Chinese Patients with Arteriosclerotic Cardiovascular Diseases:A Single-Center Study Open
View article: Plug-and-Play Recipe Generation with Content Planning
Plug-and-Play Recipe Generation with Content Planning Open
Recent pre-trained language models have shown promising capabilities in generating fluent and realistic natural language text. However, generating multi-sentence text with global content planning has been a long-existing research question.…
View article: Learning Functional Distributional Semantics with Visual Data
Learning Functional Distributional Semantics with Visual Data Open
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a numerical vector. In…
View article: Prevalence and risk factors for cerebral microbleeds in elderly Chinese people with arteriosclerotic cardiovascular diseases
Prevalence and risk factors for cerebral microbleeds in elderly Chinese people with arteriosclerotic cardiovascular diseases Open
Background: People with arteriosclerotic cardiovascular diseases (ASCVD) frequently use antithrombotic agents and statins. The objective of the study was to explore the prevalence and risk factors of cerebral microbleeds (CMB) in elderly C…
View article: Learning Functional Distributional Semantics with Visual Data
Learning Functional Distributional Semantics with Visual Data Open
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a numerical vector. In…
View article: Sustained impact of subcutaneous immunotherapy among patients with allergic rhinitis who experienced treatment delay due to the COVID‐19 pandemic: A multicenter, two‐arm, real‐world study
Sustained impact of subcutaneous immunotherapy among patients with allergic rhinitis who experienced treatment delay due to the COVID‐19 pandemic: A multicenter, two‐arm, real‐world study Open
To the editor, Subcutaneous immunotherapy (SCIT) is highly effective for seasonal pollinosis and perennial disease in patients with mite allergy.1 SCIT usually involves administering a gradually increasing dose of the specific allergens to…
View article: Learning Functional Distributional Semantics with Visual Data
Learning Functional Distributional Semantics with Visual Data Open
Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a numerical vector. In…
View article: Plug-and-Play Recipe Generation with Content Planning
Plug-and-Play Recipe Generation with Content Planning Open
Recent pre-trained language models have shown promising capability to generate fluent and realistic natural text. However, generating multi-sentence text with global content planning has been a long-existing research question. The current …
View article: Sustained impact of subcutaneous immunotherapy among patients with allergic rhinitis who experienced treatment delay due to the COVID-19 pandemic: A multicenter, two-arm, real-world study
Sustained impact of subcutaneous immunotherapy among patients with allergic rhinitis who experienced treatment delay due to the COVID-19 pandemic: A multicenter, two-arm, real-world study Open
Background: The aim of this study is to investigate the impact of COVID-19 related treatment delay on subcutaneous immunotherapy (SCIT) efficacy in patients with allergic rhinitis (AR). Methods: The study was performed in 643 patients with…
View article: Research of Library Information Security Based on Cloud Computing Platform
Research of Library Information Security Based on Cloud Computing Platform Open
Information security based on cloud computing platform is becoming one of the main concerns and challenges for library in big data era.This paper analyzes the current situation and security problems under the cloud computing platform, and …
View article: Parenchymal Infiltration in Primary Diffuse Leptomeningeal Gliomatosis: Dynamic Changes in Brain MRI
Parenchymal Infiltration in Primary Diffuse Leptomeningeal Gliomatosis: Dynamic Changes in Brain MRI Open
Primary diffuse leptomeningeal gliomatosis (PDLG) is a rare and fatal disease with no special clinical manifestations. Here, we report the dynamic brain magnetic resonance imaging (MRI) changes in a 30-year-old female PDLG patient over a 1…
View article: Research on logistics handing agv picking route optimization method based on improved genetic algorithm
Research on logistics handing agv picking route optimization method based on improved genetic algorithm Open
：Establish logistics handing agv operating environment model by using the grid method, and the picking route optimization model based on grid environment model.By analyzing the qualitative factors in agv "goods to person" picking system, p…
View article: Two cases of intracranial gliomatosis in different types: clinical manifestations and radiological features
Two cases of intracranial gliomatosis in different types: clinical manifestations and radiological features Open
Objective To report one case of gliomatosis cerebri (GC) and one case of leptomeningeal gliomatosis (LG), both of them were clearly diagnosed by brain biopsy. Methods and Results 1) The GC patient was a 4…