Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks122 from public data
- CodeBERT: A Pre-Trained Model for Programming and Natural Languages4,421
This work develops CodeBERT with Transformer-based neural architecture, and trains it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators.
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions3,965
A thorough overview of hallucination detection methods and benchmarks is presented and the promising research directions on LLM hallucinations are highlighted, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.
- Effective LSTMs for Target-Dependent Sentiment Classification1,010
Two target dependent long short-term memory models, where target information is automatically taken into account, are developed, which achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.
- A language-independent neural network for event detection282
A language-independent neural network is developed to capture both sequence and chunk information from specific contexts and use them to train an event detector for multiple languages without any manually encoded features.
- 141
- A Survey on Dialogue Summarization: Recent Advances and New Frontiers127
A thorough review of dialogue summarization according to the characteristics of each domain, covering meeting, chat, email thread, customer service and medical dialogue, as well as an overview of publicly available research datasets.
- Effective Deep Memory Networks for Distant Supervised Relation Extraction122
This paper introduces a novel neural approach for distant supervised RE with special focus on attention mechanisms, which includes two major attention-based memory components, which are capable of explicitly capturing the importance of each context word for modeling the representation of the entity pair.
- Target-Dependent Sentiment Classification with Long Short Term Memory.122
Two target dependent long short-term memory models, where target information is automatically taken into account, are developed, which achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.
- RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness115
RLAIF-V maximally explores open-source MLLMs from two perspectives, including high-quality feedback data generation for preference learning and self-feedback guidance for inference-time scaling, and reveals the self-alignment potential of open-source MLLMs, where the model can learn from feedback of itself to achieve super GPT-4V trustworthiness.
- Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization114
DialoGPT, a pre-trained model for conversational response generation, can be developed as an unsupervised dialogue annotator, which takes advantage of dialogue background knowledge encoded in DialoG PT.
- TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching110
This work proposes TableGPT, a model that outperforms existing systems on most few-shot settings for table-to-text generation and exploits multi-task learning with two auxiliary tasks that preserve table’s structural information by reconstructing the structure from GPT-2's representation and improving the text's fidelity with content matching task.
- Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration94
A training-free ensemble framework DeePEn, fusing the informative probability distributions yielded by different LLMs at each decoding step, which achieves consistent improvements across six benchmarks covering subject examination, reasoning, and knowledge.
- Semantic Parsing with Syntax- and Table-Aware SQL Generation83
The quality of the generated SQL query is significantly improved through learning to replicate content from column names, cells or SQL keywords; and improving the generation of WHERE clause by leveraging the column-cell relation.
- Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization81
A Dialogue Discourse-Dware Meeting Summarizer (DDAMS) to explicitly model the interaction between utterances in a meeting by modeling different discourse relations and a relational graph encoder, where the utterances and discourse relations are modeled in a graph interaction manner.
- Topic-to-Essay Generation with Neural Networks72
A multi-topic aware long short-term memory network that learns the weight of each topic and is sequentially updated during the decoding process and has the ability to generate essays that are not only coherent but also closely related to the input topics.
- Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)65
This work develops a table cell fusion gate to combine representations from row, column and time dimension into one dense vector according to the saliency of each dimension’s representation.
- Improving Low Resource Named Entity Recognition using Cross-lingual Knowledge Transfer65
A lexicon extension strategy is designed to address out-of lexicon problem by automatically learning semantic projections and regard word-level entity type distribution features as an external language-independent knowledge and incorporate them into the neural architecture.
- 61
- Retrieval-Generation Synergy Augmented Large Language Models58
This work proposes an iterative retrieval-generation collaborative framework that is not only able to leverage both parametric and non-parametric knowledge, but also helps to find the correct reasoning path through retrieval- generation interactions, which is very important for tasks that require multi-step reasoning.
- Adaptive Multi-pass Decoder for Neural Machine Translation57
A novel architecture called adaptive multi-pass decoder is proposed, which introduces a flexible multi- pass polishing mechanism to extend the capacity of NMT via reinforcement learning and adopts an extra policy network to automatically choose a suitable and effective number of decoding passes.
- Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks56
A novel multi-speaker dialogue summarizer to demonstrate how large-scale commonsense knowledge can facilitate dialogue un-derstanding and summary generation and a Dialogue Heterogeneous Graph Network for modeling both information.
- Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications55
A review to discuss the trends in integration of knowledge and large language models, including taxonomy of methods, benchmarks, and applications is proposed, with the intention of inspiring future research endeavors.
- Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding46
A survey of extrapolatable PEs that have dominated this research field, covering position interpolation and randomized position methods, aims to enable the reader to gain a deep understanding of existing methods and provide stimuli for future research.
- 42
- Aligning Semantic in Brain and Language: A Curriculum Contrastive Method for Electroencephalography-to-Text Generation37
A Curriculum Semantic-aware Contrastive Learning strategy (C- SCL), which effectively recalibrates the subject-dependent EEG representation to the semantic- dependent EEG representation, thereby reducing the discrepancy.
- Enhancing Neural Data-To-Text Generation Models with External Background Knowledge37
This paper enhances neural data-to-text models with external knowledge in a simple but effective way to improve the fidelity of generated text by attends to relevant external knowledge, encoded as a temporary memory, and combines this knowledge with the context representation of data before generating words.
- Learning to Rewrite for Non-Autoregressive Neural Machine Translation36
An architecture named RewriteNAT is proposed to explicitly learn to rewrite the erroneous translation pieces by utilizing a locator module to locate the erroneous ones, which are then revised into the correct ones by a revisor module.
- Rep-Mamba: Re-Parameterization in Vision Mamba for Lightweight Remote Sensing Image Super-Resolution35
- SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment29
This work proposes an efficient multilingual reasoning alignment approach that precisely identifies and fine-tunes the layers responsible for handling multilingualism and shows that the method, SLAM, only tunes 6 layers' feed-forward sub-layers, achieving superior average performance than all strong baselines across 10 languages.
- MSAMSum: Towards Benchmarking Multi-lingual Dialogue Summarization28
A multi-lingual dialogue summarization dataset, namely MSAMSum, which covers dialogue-summary pairs in six languages using sophisticated translation techniques and employs two methods to ensure the integral translation quality and summary factual consistency.
- Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning26
This work aims to learn a neural semantic parser when only prior knowledge about a limited number of simple rules is available, without access to either annotated programs or execution results, and improves the accuracy and stability on examples uncovered by rules.
- Dialogue Discourse-Aware Graph Convolutional Networks for Abstractive Meeting Summarization.24
A Dialogue Discourse-Aware Graph Convolutional Networks (DDA-GCN) for meeting summarization is developed by utilizing dialogue discourse, which is a dialogue-specific structure that can provide pre-defined semantic relationships between each utterance.
- Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification22
This paper proposes to enhance neural content planning by understanding data values with contextual numerical value representations that bring the sense of value comparison into content planning; and verifying the importance and ordering of the selected sequence of records with policy gradient.
- Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning21
A novel trainingive with an abstention mechanism, in which the model learns to selectively reject tokens that misalign with the desired knowledge distribution via a special [REJ] token, that effectively alleviates hallucinations caused by knowledge mis-alignment.
- 21
- 20
- Improving Controllable Text Generation with Position-Aware Weighted Decoding20
A novel framework based on existing weighted decoding methods called CAT-PAW is proposed, which introduces a lightweight regulator to adjust bias signals from the controller at different decoding positions to solve the control strength/fluency trade-off problem.
- 19
- Knowledge-Aware Conversational Semantic Parsing over Web Tables14
A knowledge-aware semantic parser to improve parsing performance by integrating various types of knowledge, including grammar knowledge, expert knowledge, and external resource knowledge, which is based on a decomposable model.
- English-Chinese Knowledge Base Translation with Neural Network13
A neural network approach is presented, which learns continuous triple representation with a gated neural network, which improves translation accuracy compared with baseline methods and shows that adaptive composition model improves standard solution such as neural tensor network in terms of translation accuracy.
- Pretraining without wordpieces: learning over a vocabulary of millions of words12
This work explores to develop a BERT-style pretrained model over a vocabulary of words instead of wordpieces, called WordBERT, which makes significant improvements on cloze test and machine reading comprehension and has comparable time cost to BERT in natural language understanding tasks.
- Enhanced Neural Machine Translation by Joint Decoding with Word and POS-tagging Sequences12
This paper improves the performance of neural machine translation with shallow syntax of target language, which has better accuracy and latency than deep syntax such as dependency parsing, and takes less parameters and runtime than other complex machine translation models.
- 11
- Adapter-Based Selective Knowledge Distillation for Federated Multi-Domain Meeting Summarization11
An adapter-based summarization model where two adapters cooperatively facilitate learning using fewer parameters to reduce communication costs is developed, and a selective knowledge distillation strategy is devised, assisting clients in robustly handling domain-focused modelling on their own data, while leveraging global parameters based on non-IID data.
- Bitext Name Tagging for Cross-lingual Entity Annotation Projection11
This paper focuses on the named entity recognition (NER) task and proposes a weakly-supervised framework to project entity annotations from English to IL through bitexts, which combines advantages of rule-based methods and deep learning methods.
- Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective10
Experimental results on the XT-VQA demonstrate that MVCL-MI effectively reduces the visual-text cross-lingual performance disparity while preserving the inherent capabilities of LVLMs, shedding new light on the potential practice for improving LVLMs.
- 10
- Length Controlled Generation for Black-box LLMs9
A novel iterative sampling framework for text length control, integrating the Metropolis-Hastings algorithm with an importance sampling acceleration strategy, which efficiently and reliably regulates L LM s to generate length-constrained text without modifying the underlying parameters, thereby preserving the original capabilities of L LM s.
- 9
- Semantic-aware Contrastive Learning for Electroencephalography-to-Text Generation with Curriculum Learning9
A Curriculum Semantic-aware Contrastive Learning strategy (C-SCL), which effectively re-calibrates the subject-dependent EEG representation to the semantic- dependent EEG representation, thus reducing the discrepancy.
- 8
- 8
- Unifying the Convergences in Multilingual Neural Machine Translation8
A novel training strategy named LSSD (LanguageSpecific Self-Distillation), which can alleviate the convergence inconsistency and help MNMT models achieve the best performance on each language pair simultaneously.
- 7
- Learning to refine source representations for neural machine translation7
A novel encoder–refiner–decoder framework, which dynamically refines the source representations based on the generated target-side information at each decoding step, and a policy network to decide when to refine at specific decoding steps is proposed.
- Multi-level cross-lingual attentive neural architecture for low resource name tagging7
This paper combines multi-level cross-lingual knowledge as attention into a neural architecture, which guides low resource name tagging to achieve a better performance and is able to yield improvements in name tagging over all previous baselines.
- CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation6
A few-shot transfer learning strategy is proposed that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training.
- Digital Human Techniques for Education Reform6
Analysis of the application of Digital Human Technique in education reform indicates that it significantly enhances the learning experience by enabling personalized teaching, increasing engagement, and fostering emotional connections.
- 6
- 5
- Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation5
An unsupervised neural model with interactive attention mechanism is presented, used for learning the semantic relationship between records and reference texts to achieve better content transfer and better style preservation.
- Table-to-Text Generation via Row-Aware Hierarchical Encoder5
Three extractive evaluation metrics and human evaluation show that the proposed neural model has the ability to select salient records and the generated game summary is more accurate.
- 4
- 4
- 4
- 4
- 3
- LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning3
LangGPS is proposed, a lightweight two-stage pre-selection framework guided by language separability which quantifies how well samples in different languages can be distinguished in the model's representation space and applying LangGPS on top of existing selection methods improves their effectiveness and generalizability in multilingual training.
- 3
- The Role of Summarization in Generative Agents: A Preliminary Perspective3
This report presents an integrated perspective on comprehendingGenerative agents through summarization, since it believes summarization is the most fundamental and indispensable capacity of generative agents manifested across diverse scenarios.
- 3
- Quality Control for Distantly-Supervised Data-to-Text Generation via Meta Learning3
This work is the first to alleviate the noise in distantly-supervised data-to-text generation via meta learning and can generate more grammatically correct and more faithful text compared to the state-of-the-art DSG model.
- 3
- Improved Neural Machine Translation with POS-Tagging Through Joint Decoding3
Three NMT decoding models are presented to jointly predict target word and POS tag sequences and it is shown that the fully shared decoder can acquire the best performance.
- 2
- 2
- 2
- 2
- Relay Decoding: Concatenating Large Language Models for Machine Translation2
An innovative approach called RD (Relay Decoding), which entails concatenating two distinct large models that individually support the source and target languages, achieves superior results in the machine translation task.
- 2
- 2
- 2
- 2
- Dialogue Context Modelling for Action Item Detection: Solution for ICASSP 2023 Mug Challenge Track 52
- 2
- 2
- 1
- 1
- Exploring Cross-Lingual Latent Transplantation: Mutual Opportunities and Open Challenges1
This paper introduces and investigates cross-lingual latent transplantation, a probing framework which aims to further exploit the model’s internalized multilingual knowledge during inference and examine its effects on the multilingual capability and cultural adaptability of LLMs.
- 1
- 1
- One for All: Update Parameterized Knowledge Across Multiple Models1
A novel ensemble-based approach that employs a plug-in model as the editing module, enabling stable knowledge updates across multiple models, and incorporates an ensemble enhancement mechanism to mitigate the excessive reliance on the central model inherent in the model ensemble technique, making it more suitable for knowledge editing.
- 1
- Emage: Non-Autoregressive Text-to-Image Generation1
This work explores non-autoregressive text-to-image models that efficiently generate hundreds of image tokens in parallel and runs 16 times to generate images of competitive quality with an order of magnitude lower inference latency.
- CT radiomics signature: a potential biomarker for fibroblast activation protein expression in patients with pancreatic ductal adenocarcinoma1
The XGBoost classifier based on CT radiomics in the portal venous phase can non-invasively predict FAP expression and may help to improve clinical decision-making in patients with PDAC.
- Learning number reasoning for numerical table-to-text generation1
This paper proposes a neural architecture called Neural Table Reasoning Generator (NTRG), with an additional switching gate as well as a specifically designed equation decoder for generating mathematical equations adaptively and presents a pre-training strategy similar to the mask language model.
- 1
- –
- –
- –
- –
- –
- Rethinking Thinking Steps in Overthinking: Towards More Effective Reasoning–
This work proposes a training-free, interpretable framework that selects thinking words via attention heads to guide LRMs toward more effective reasoning, and consistently outperforms the strong baseline DEER.
- –
- –
- –
- –
- –
- –
- –
- –
- Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models–
- –
- –
- SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills–
A general multilingual multitask model, named SkillNet-X, which enables a single model to tackle many different tasks from different languages, and shows that SkillNet-X performs better than task-specific and two multitask learning baselines.
- –
- DiffuD2T: Empowering Data-to-Text Generation with Diffusion–
This paper uses the diffusion model to improve the prefix tuning for data-to-text generation and proposes a look-ahead guiding loss to supervise the iterative refinement process for better text generation.
- Anterior Umbilication of Lens in a Family with Congenital Cataracts Associated with a Missense Mutation of MIP Gene–
This is the first report on the anterior umbilication of the lens with nuclear or total opacity caused by the c.97C > T (p.R33C) variant in the MIP gene, and results provide evidence that the elongated axial length might be associated with this variant.
- Wide band infrared spectral engine based on digital micro-mirror device–
A wide-band infrared spectral engine based on spatial light modulator (SLM) is developed, comprised of a blackbody IR source, a Digital Micromirror Device (DMD) and some optical components, and it is capable of generating the spectral distributions with programming each of the DMD’s spatial pixels.
- –
- –
- –
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 2026-10-14. 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.