Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks77 from public data
- Large language models for generative information extraction: a survey507
This study surveys the most recent advancements in generative Large Language Models efforts for IE tasks and identifies several insights in technique and promising research directions that deserve further exploration in future studies.
- DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation136
The proposed DISC-MedLLM is a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services, surpassing existing medical LLMs in both single-turn and multi-turn consultation scenarios.
- Model Compression and Efficient Inference for Large Language Models: A Survey110
This paper investigates compression and efficient inference methods for large language models from an algorithmic perspective, and distinguishes large language models into medium models and ``real'' large models.
- 106
- A benchmark for automatic medical consultation system: frameworks, tasks and datasets93
This article creates a new large medical dialogue dataset with multi-level fine-grained annotations and establishes five independent tasks, including named entity recognition, dialogue act classification, symptom label inference, medical report generation and diagnosis-oriented dialogue policy.
- DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning85
This work proposes Multiple Experts Fine-tuning Framework, a methodology that improves general LLMs by endowing them with multi-turn question answering abilities, domain text processing capabilities, mathematical computation skills, and retrieval-enhanced generation capabilities.
- Water-Soluble Degradable Hyperbranched Polyesters: Novel Candidates for Drug Delivery?82
A novel approach to hyperbranched polymers is presented in this work, where addition of diethanolamine or N-methyl-d-glucamine to methyl acrylate (AB) generates dominantly AD(n)-type intermediates.
- CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation81
A multi-factor hierarchical framework, CoMAE, is proposed, which models the above three key factors of empathy expression in a hierarchical way and can generate more empathetic responses than previous methods.
- Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning78
This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs) by conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text understanding to embracing multiple modalities, and demonstrates that selectively tuning only with conversational data can improve efficiency further.
- Towards an Online Empathetic Chatbot with Emotion Causes62
The proposed empathetic chatbot is developed and compared with several SOTA methods using automatic metrics, expert-based human judgements as well as user-based online evaluation to verify the effectiveness of the proposed approach.
- DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation59
A new dialog pre-training framework called DialogVED is proposed, which introduces continuous latent variables into the enhanced encoder-decoder pre- training framework to increase the relevance and diversity of responses.
- Test of the Universal Scaling Law of Diffusion in Colloidal Monolayers51
It is found that the universal scaling law with α=1 holds well for highly charged polystyrene spheres suspended at an air-water interface, where the strong electrostatic interactions play a dominant role.
- Evidence of nematic order and nodal superconducting gap along [110] direction in RbFe2As249
A scanning tunneling microscopy study on RbFe2As2, a heavily hole-doped Fe-based superconductor (FeSC), suggests a novel (π, π) nematic phase emerging, suggesting an intimate connection between nematicity and superconducting pairing in iron-basedsuperconductors.
- Adapting Translation Models for Transcript Disfluency Detection46
This paper proposes a fast non-autoregressive TDD model following the non- autoregressive NMT model emerged recently, and shows that the proposed model significantly outperforms previous state-of-the-art models.
- Enhanced probabilistic analytical target cascading with application to multi-scale design37
The EPATC approach outperforms the original PATC by providing more accurate optimal solutions and is shown to be more effective and efficient than the current PATC approach.
- Hierarchical reinforcement learning for automatic disease diagnosis32
Inspired by the offline consultation process, this work proposes to integrate a hierarchical policy structure of two levels into the dialogue system for policy learning that achieves higher accuracy and symptom recall in disease diagnosis compared with existing systems.
- DxFormer: a decoupled automatic diagnostic system based on decoder–encoder transformer with dense symptom representations25
A new automatic diagnostic framework called DxFormer is proposed, which decouples symptom inquiry and disease diagnosis, so that these two modules can be independently optimized and achieves the state-of-the-art diagnostic accuracy.
- 22
- EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning19
An Entity-Agnostic Representation Learning (EARL) method to introduce knowledge graphs to informative conversation generation and demonstrates that this model can generate more informative, coherent, and natural responses than baseline models.
- 18
- EnsembleGAN18
This paper proposes ensembleGAN, an adversarial learning framework for enhancing a retrieval-generation ensemble model in open-domain conversation scenario that consists of a language-model-like generator, a ranker generator, and one ranker discriminator.
- End-to-End Conversational Search for Online Shopping with Utterance Transfer16
ConvSearch is proposed, an end-to-end conversational search system that deeply combines the dialog system with search, which leverages the text profile to retrieve products, which is more robust against imperfect product schema/knowledge compared with using product attributes alone.
- Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension15
This paper proposes a joint framework that unifies these two tasks, sharing the same encoder to extract the common and task-invariant features with different decoders to learn task-specific features, and augments the Transformer architecture with a memory updater, designed to selectively store and update the history dialog information so as to support downstream tasks.
- Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations14
This paper proposes a Contextual Fine-to-Coarse (CFC) distilled model for coarse-grained response selection in open-domain conversations and shows that the proposed method achieves huge improvement over all evaluation metrics compared with traditional baseline methods.
- Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models13
This study evaluates the instruction-following capabilities of various retrieval models beyond content relevance, including LLM-based dense retrieval and reranking models and develops InfoSearch, a novel retrieval evaluation benchmark spanning six document-level attributes, and introduces novel metrics.
- 12
- A MADDPG-based multi-agent antagonistic algorithm for sea battlefield confrontation11
A sea battlefield game confrontation decision algorithm based on multi-agent deep deterministic policy gradient that combines long short-term memory and actor-critic, which not only realizes the convergence of the algorithm in huge state space and action space, but also solves the problem of sparse real rewards.
- Overview of SMP-CAIL2020-Argmine: The Interactive Argument-Pair Extraction in Judgement Document Challenge11
The results of the Interactive Argument-Pair Extraction in Judgement Document Challenge held by both the Chinese AI and Law Challenge (CAIL) and the Chinese National Social Media Processing Conference (SMP) are presented, and the related data set - SMP-CAIL2020-Argmine is introduced.
- 10
- Simplified Readability Metric Drives Improvement of Radiology Reports: an Experiment on Ultrasound Reports at a Pediatric Hospital10
Although the degree of improvement varied for different measures, it is evident that targeted training could provide potential benefits to improve readability due to the statistically significant results.
- Interpretable machine learning model based on CT semantic features and radiomics features to preoperatively predict Ki-67 expression in gastrointestinal stromal tumors9
The interpretable SVM model can predict Ki-67 expression of GISTs patients individually before surgery, which can provide reliable imaging biomarkers for clinical treatment decisions.
- 8
- Recognizing Young Readers' Spoken Questions8
This work adopts the framework of predictable response training, which aims at simultaneously achieving linguistic predictability and educational utility, and design instruction in this framework to teach children the reading comprehension strategy of self-questioning.
- 7
- Emotional dialog generation via multiple classifiers based on a generative adversarial network7
The proposed EMC-GAN model is capable of generating consistent, smooth, and fluent dialog that conveys pre-specified emotions, and exhibits better performance with respect to emotional accuracy, consistency, and fluency compared to its competitors.
- Focus-Constrained Attention Mechanism for CVAE-based Response Generation7
This work proposes a focus-constrained attention mechanism to take full advantage of focus in well aligning the input to the target response and demonstrates that by exploiting the fine-grained signal, this model can generate more diverse and informative responses compared with several state-of-the-art models.
- Computerized “Learn-As-You-Go” classification of traumatic brain injuries using NEISS narrative data7
The results suggest that the DUALIST “Learn-As-You-Go” program, which features a user-friendly online interface, is effective in injury narrative classification.
- An Advanced Driver Assistance Test Cases Generation Methodology Based on Highway Traffic Situation Description Ontologies6
This work proposes a methodology to generate automatically test cases of autonomous vehicle for highway based on a three layers hierarchy, which exploits static and mobile concepts defined in the context of three ontologies: highway, weather and vehicle.
- The Application of BIM in Small and Medium-sized Smart Substation—A Case Study of Prefabricated Building Design6
A new mode of communication on the project of small and medium-sized smart substation with BIM, involving the 3D visualization, parametric modeling and interoperability, and the process for creating models of prefabricated steel frame building in substation are researched.
- The analysis of generative adversarial network in sports education based on deep learning5
The use of Generative Adversarial Network (GAN) technology in deep learning to evaluate the mental health qualities of college and university students through the unique avenue of sports aims to advance the level of mental health education among college and university students in the sports domain.
- 4
- FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation4
A real-world fine-grained domain adaptation task in machine translation (FGraDA) is presented and in-depth analyses are presented showing that there are still challenging problems to further improve the performance with heterogeneous resources.
- 4
- 4
- Inferring Emphasis for Real Voice Data: An Attentive Multimodal Neural Network Approach4
An attentive multimodal neural network is proposed that trains an emphasis classifier by attending on the textual features with an attention-based bidirectional long short-term memory network (ABLSTM), to comprehensively learn discriminative features from diverse users.
- An Emulator for Executing IA-32 Applications on ARM-Based Systems4
The design and implementation of TransARM-IU, a use-level ISA emulator that supports IA-32 applications on ARMbased systems is described and a hybrid threaded interpretation method is proposed to improve the efficiency of the emulator.
- 3
- KNSE: A Knowledge-aware Natural Language Inference Framework for Dialogue Symptom Status Recognition3
- DGQAN3
The proposed dual graph question-answer attention networks (DGQAN) for answer selection task achieves state-of-the-art performance on three datasets (SemEval-2015, 2016, and 2017), outperforming all the baseline models.
- 3
- Study on audit evidence gathering based on partition and outlier detection3
An audit evidence gathering method which first used data partition and then adopted improved outlier detection to deal with the huge audit data and shows that with this method the hidden information is easily found in thehuge audit data, and the efficiency of outlier Detection is greatly improved, thereby the efficiencyof the audit is enhanced.
- 2
- 2
- Free heterotic string field theory2
A gauge-fixed action is constructed for the free heterotic string based on the bosonic string and the Neveu-Schwarz-Ramond (NSR) superstring by the Becchi-Rouet-Stora-Tyutin approach to eliminate the tachyons and to ensure that the states have the correct spin statistics.
- 1
- 1
- 1
- 1
- 1
- ESN-NER: entity storage network using attention mechanism for chinese NER1
This work designs an entity storage layer in this model to extract and store the entity information as a local linguistic feature, and design a position feature which is generated by four flags to enhance the learning of boundary.
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- The Optimization Design of Missile Maintenance Process Based on PERT Analysis–
The article adopted the PERT simulation analysis to optimize the maintenance procedure of the missile based on the network model to make us understand the problem should be pay attention to when modeling, then take corresponding measures to solve the problem.
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.