Jingping Liu
YOU?
Author Swipe
View article: MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs
MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs Open
Open-ended question answering (QA) is a key task for evaluating the capabilities of large language models (LLMs). Compared to closed-ended QA, it demands longer answer statements, more nuanced reasoning processes, and diverse expressions, …
View article: IMQC: A Large Language Model Platform for Medical Quality Control
IMQC: A Large Language Model Platform for Medical Quality Control Open
Medical quality control (MQC) indicators are essential for evaluating the performance of healthcare institutions to ensure high-quality patient care. In this paper, we report the design, implementation, and deployment of the Intelligent EM…
View article: CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation
CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation Open
Medical quality control indicators are essential to assess the qualifications of healthcare institutions for medical services. With the impressive performance of large language models (LLMs) like GPT-4 in the medical field, leveraging thes…
View article: Can Multimodal Large Language Models Understand Spatial Relations?
Can Multimodal Large Language Models Understand Spatial Relations? Open
Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or all…
View article: MSDiagnosis: A Benchmark for Evaluating Large Language Models in Multi-Step Clinical Diagnosis
MSDiagnosis: A Benchmark for Evaluating Large Language Models in Multi-Step Clinical Diagnosis Open
Clinical diagnosis is critical in medical practice, typically requiring a continuous and evolving process that includes primary diagnosis, differential diagnosis, and final diagnosis. However, most existing clinical diagnostic tasks are si…
View article: Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency
Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency Open
Previous works of negation understanding mainly focus on negation cue detection and scope resolution, without identifying negation subject which is also significant to the downstream tasks. In this paper, we propose a new negation triplet …
View article: Beyond Entities: A Large-Scale Multi-Modal Knowledge Graph with Triplet Fact Grounding
Beyond Entities: A Large-Scale Multi-Modal Knowledge Graph with Triplet Fact Grounding Open
Much effort has been devoted to building multi-modal knowledge graphs by visualizing entities on images, but ignoring the multi-modal information of the relation between entities. Hence, in this paper, we aim to construct a new large-scale…
View article: Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation Open
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge.…
View article: Exploiting Duality in Open Information Extraction with Predicate Prompt
Exploiting Duality in Open Information Extraction with Predicate Prompt Open
Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence. Compared with general information extraction (IE), OpenIE poses more chal…
View article: Pre-matching study of the natural gas engine turbocharging system based on the coupling of experiments and numerical simulation
Pre-matching study of the natural gas engine turbocharging system based on the coupling of experiments and numerical simulation Open
In this study, a pre-matching method was developed based on measured performance parameters and theoretical calculations of turbochargers. First, the turbocharger of a natural gas engine was subjected to a comprehensive performance experim…
View article: A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics
A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics Open
Text-to-image (T2I) synthesis has recently achieved significant advancements. However, challenges remain in the model's compositionality, which is the ability to create new combinations from known components. We introduce Winoground-T2I, a…
View article: Towards Visual Taxonomy Expansion
Towards Visual Taxonomy Expansion Open
Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual semantics, leading to an inability to generalize to unseen ter…
View article: M3PT: A Multi-Modal Model for POI Tagging
M3PT: A Multi-Modal Model for POI Tagging Open
POI tagging aims to annotate a point of interest (POI) with some informative\ntags, which facilitates many services related to POIs, including search,\nrecommendation, and so on. Most of the existing solutions neglect the\nsignificance of …
View article: GANTEE: Generative Adversarial Network for Taxonomy Enterance Evaluation
GANTEE: Generative Adversarial Network for Taxonomy Enterance Evaluation Open
Taxonomy is formulated as directed acyclic graphs or trees of concepts that support many downstream tasks. Many new coming concepts need to be added to an existing taxonomy. The traditional taxonomy expansion task aims only at finding the …
View article: End-to-End Entity Linking with Hierarchical Reinforcement Learning
End-to-End Entity Linking with Hierarchical Reinforcement Learning Open
Entity linking (EL) is the task of linking the text segments to the referring entities in the knowledge graph, typically decomposed into mention detection, and entity disambiguation. Compared to traditional methods treating the two tasks s…
View article: QUERT: Continual Pre-training of Language Model for Query Understanding in Travel Domain Search
QUERT: Continual Pre-training of Language Model for Query Understanding in Travel Domain Search Open
In light of the success of the pre-trained language models (PLMs), continual pre-training of generic PLMs has been the paradigm of domain adaption. In this paper, we propose QUERT, A Continual Pre-trained Language Model for QUERy Understan…
View article: Development and Validation of a Variable Displacement Variable Compression Ratio Miller Cycle Technology on an Automotive Gasoline Engine
Development and Validation of a Variable Displacement Variable Compression Ratio Miller Cycle Technology on an Automotive Gasoline Engine Open
At partial load, traditional automotive gasoline engines have high pumping losses due to the throttling of the intake charge for load control. Variable Valve Timing (VVT) and the introduction of externally cooled EGR could reduce the pumpi…
View article: MMpedia: A Large-scale Multi-modal Knowledge Graph
MMpedia: A Large-scale Multi-modal Knowledge Graph Open
List of files: entity2image.json: The entity to map images file MMpedia_triples.ttl: The triples file EntlistXX.tar: The image file MMpedia dataset is split into 132 subsets and each subset is compressed into a .tar file. After unziping fi…
View article: GANTEE: Generative Adversatial Network for Taxonomy Entering Evaluation
GANTEE: Generative Adversatial Network for Taxonomy Entering Evaluation Open
Taxonomy is formulated as directed acyclic concepts graphs or trees that support many downstream tasks. Many new coming concepts need to be added to an existing taxonomy. The traditional taxonomy expansion task aims only at finding the bes…