Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks87 from public data
- Exploiting BERT for End-to-End Aspect-based Sentiment Analysis335
This work builds a series of simple yet insightful neural baselines to deal with E2E-ABSA, and shows that even with a simple linear classification layer, the BERT-based architecture can outperform state-of-the-art works.
- Aspect Sentiment Quad Prediction as Paraphrase Generation314
This work introduces the Aspect Sentiment Quad Prediction (ASQP) task, aiming to jointly detect all sentiment elements in quads for a given opinionated sentence, and proposes a novel Paraphrase modeling paradigm to cast the ASQP task to a paraphrase generation process.
- 312
- Towards Generative Aspect-Based Sentiment Analysis306
This paper proposes to tackle various ABSA tasks in a unified generative framework with two types of paradigms, namely annotation-style and extraction-style modeling, to enable the training process by formulating each ABSA task as a text generation problem.
- Multilingual Jailbreak Challenges in Large Language Models283
Experimental results show that ChatGPT fine-tuned with such data can achieve a substantial reduction in unsafe content generation, and a novel self-defense framework that automatically generates multilingual training data for safety fine-tuning is proposed.
- M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models149
This work introduces M3Exam, a novel benchmark sourced from real and official human exam questions for evaluating LLMs in a multilingual, multimodal, and multilevel context, and finds that current models, including GPT-4, still struggle with multilingual text, particularly in low-resource and non-Latin script languages.
- Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching81
This paper considers the unsupervised cross-lingual transfer for the ABSA task, where only labeled data in the source language is available and aims at transferring its knowledge to the target language having no labeled data and proposes an alignment-free label projection method.
- A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning68
It is argued that the pretrained feature extractor itself can be strong enough to achieve a competitive or even better continual learning performance on Split-CIFAR100 and CoRe 50 benchmarks and a simple baseline is designed that achieves 88.53% on 10-Split-CifAR-100, surpassing most state-of-the-art continual learning methods that are all initialized using the same pretrained transformer model.
- Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems62
This paper investigates how a neural network understands patterns only from semantics, and proposes a contrastive learning approach, where the neural network perceives the divergence of patterns.
- Toward Personalized Answer Generation in E-Commerce via Multi-perspective Preference Modeling49
Experimental results on real-world E-commerce QA datasets demonstrate that the proposed Personalized Answer GEneration method outperforms existing methods by generating informative and customized answers and show that answer generation in E-Commerce can benefit from personalization.
- 38
- 38
- Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modeling35
This paper proposes an answer ranking model named MUSE which carefully models multiple semantic relations among the question, answers, and relevant reviews, and achieves superior performance on the concerned answer ranking task.
- Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models34
A supervised learning framework called Bi-Factorial Preference Optimization is proposed, which re-parameterizes a joint RLHF objective of both safety and helpfulness into a single supervised learning objective and significantly outperforms existing approaches in both safety and helpfulness.
- Nonfactoid Question Answering as Query-Focused Summarization With Graph-Enhanced Multihop Inference34
A novel query-focused summarization method, namely a graph-enhanced multihop query- focused summarizer (GMQS), to tackle the nonfactoid QA problem and possesses the capability of performing explainable multihip reasoning.
- Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce33
Two kinds of opinion fusion strategies, namely, static and dynamic fusion, are proposed to distill and aggregate important opinion information learned from the opinion mining task into the answer generation process.
- The concept of decentralized and secure electronic marketplace33
The concept of Decentralized Electronic Marketplace (DEM) is proposed which allow buyers and sellers to engage in commercial transactions, subject to an explicitly stated set of trading rules, called the law of this marketplace—which they can trust to be observed by their trading partners.
- AnswerFact: Fact Checking in Product Question Answering32
This paper introduces AnswerFact, a large scale fact checking dataset from product question answering forums, and proposes a novel neural model with tailored evidence ranking components to handle the concerned answer veracity prediction problem.
- 31
- Overcoming Generic Knowledge Loss with Selective Parameter Update30
This work proposes a novel approach that, instead of updating all parame-ters equally, localizes the updates to a sparse set of parame-ters relevant to the task being learned, striking a balance between efficiency and new task performance, while main-taining the transferability and generalizability of foundation models.
- Aspect-based Sentiment Analysis in Question Answering Forums30
A model with a design of cross-sentence aspect-opinion interaction modeling to address the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair.
- 26
- 25
- 23
- Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers22
Babel is introduced, an open multilingual LLM that covers the top 25 languages by number of speakers, supports over 90% of the global population, and includes many languages neglected by other open multilingual LLMs and sets a new standard for open multilingual LLMs.
- Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions22
The Auto-Arena of LLMs is innovatively proposed, which automates the entire evaluation process with LLM agents, and shows the highest correlation with human preferences, providing a promising alternative to human evaluation platforms.
- Multi-hop Inference for Question-driven Summarization22
This work proposes a novel question-driven abstractive summarization method, Multi-hop Selective Generator (MSG), to incorporate multi-hop reasoning into question- driven summarization and, meanwhile, provide justifications for the generated summaries.
- Review-guided Helpful Answer Identification in E-commerce22
The Review-guided Answer Helpfulness Prediction (RAHP) model is proposed that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds’ opinions reflected in the reviews, which is another important factor to identify helpful answers.
- Establishing Global Properties of Multi-Agent Systems Via Local Laws22
This paper shows how local laws over a MAS can be used to establish global and aggregate system properties in a scalable manner; where by "aggregate properties" the authors mean properties defined over the coincidental interactions among several, possibly many, members of a given multiagent system.
- Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization18
This paper designs a hierarchical compare-aggregate method to integrate the interaction between QA pairs in both word-level and sentence-level into the final question and answer representations and conducts the question-aware sequential extractor to produce a summary for the lengthy answer.
- Bridging the Information Gap Between Domain-Specific Model and General LLM for Personalized Recommendation16
An information sharing module is proposed which serves as an information storage mechanism and also acts as a bridge for collaborative training between the LLMs and domain-specific models to improve the performance of LLM-based recommendation with the help of user behavior pattern information mined by domain- specific models.
- 14
- 14
- SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages13
- SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia13
The first large audio-language model (LALM) tailored for multiple Southeast Asian languages-Indonesian, Thai, Vietnamese, English, and Chinese-alongside English and Chinese is introduced, showing that SeaLLMs-Audio achieves competitive performance compared with other LALMs on SEA languages.
- Label Delay in Online Continual Learning13
A new continual learning framework with explicit modeling of the label delay between data and label streams over time steps is introduced, showing experimentally that the method is the least affected by the labeldelay factor and in some cases successfully recovers the accuracy of the non-delayed counterpart.
- 11
- 9
- 9
- Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation8
DietCL outperforms, by a large margin, all existing supervised CL algorithms as well as more recent continual semi-supervised methods, and meticulously allocates computational budget for both unlabeled and labeled data jointly.
- JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning8
JsonTuning is introduced, a structure-to-structure approach that uses JSON structures to represent tasks that improves generalization by clarifying task elements and their relations, boosts robustness by minimizing ambiguity, and enhances controllability by allowing precise control over outputs.
- From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader8
Although conceptually simple, PMR is particularly effective in solving extraction tasks including Extractive Question Answering and Named Entity Recognition, where it shows tremendous improvements over previous approaches especially under low-resource settings.
- 8
- Discovery of novel triphenylphosphonium conjugated pleuromutilin with enhanced anti-MRSA effect and broaden antibacterial spectrum7
Mechanical studies revealed that a5 disrupted bacterial membranes and biofilms by elevating intracellular ROS levels-a mechanism distincts from conventional pleuromutilins, which primarily target ribosomal proteins, which primarily target ribosomal proteins.
- PEAR: Phase Entropy Aware Reward for Efficient Reasoning7
A consistent positive correlation between model entropy and response length at different reasoning stages across diverse LRMs is revealed: the thinking phase exhibits higher entropy, reflecting exploratory behavior of longer responses, while the final answer phase shows lower entropy, indicating a more deterministic solution.
- Paths towards time evolution with larger neural-network quantum states7
It is demonstrated that one can use K-FAC or minSR in conjunction with p-tVMC to reduce the computational complexity of the stochastic reconfiguration approach, thus allowing the use of these techniques for neural networks with more parameters.
- 7
- Sensors fault diagnosis of bearingless permanent magnet synchronous motor based on GAF-pCNN-BiLSTM6
Experimental results demonstrate that the proposed method not only ensures precise fault identification but also significantly outperforms other machine-learning-based fault diagnosis approaches in terms of classification performance, thereby confirming its feasibility and reliability.
- Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels6
This study proposes a new paradigm termed zero-to-strong generalization, which iteratively prompt LLMs to annotate unlabeled data and retain high-quality labels by filtering and indicates that this paradigm is effective for both in-context learning and fine-tuning, and for various model sizes.
- 6
- Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation6
A novel and easy-to-apply data augmentation strategy, namely Bilateral Generation (BiG), with a contrastive training objective for improving the performance of ranking question answer pairs with existing labeled data.
- 6
- Continual Zero-Shot Learning through Semantically Guided Generative Random Walks5
This paper introduces generalization-bound tools and provides the first theoretical explanation for the benefits of generative modeling to CZSL tasks, and proposes a learning algorithm that employs a novel semantically guided Generative Random Walk (GRW) loss.
- 4
- 4
- 4
- Enhancing Few-shot NER with Prompt Ordering based Data Augmentation4
This paper proposes a simple but effective Prompt Ordering based Data Augmentation (PODA) method to improve the training of unified autoregressive generation frameworks under few-shot NER scenarios.
- Answering Product-related Questions with Heterogeneous Information4
A novel framework to tackle the PQA task via exploiting heterogeneous information including natural language text and attribute-value pairs from two information sources of the concerned product, namely product details and user reviews is proposed.
- 3
- 3
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- Intra-/Inter-Interaction Network with Latent Interaction Modeling for Multi-turn Response Selection1
This work proposes Intra-/Inter-Interaction Network (I^3) with latent interaction modeling to comprehensively model multi-level interactions between the utterance context and the response.
- Non-hierarchical Relation Extraction of Chinese Text Based on Scalable Corpus1
A scalable corpus model is put forward, which uses Tongyici Cilin and word2vec to calculate terms’ similarity and add the qualified candidate terms to the corpora, which can expand the scalable corpus while extracting non-hierarchical relations.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Governance-based management of open distributedsystems–
It is argued standard-based approach to managing open systems based on WSDM is unreliable and inflexible, and it does not have enough ability to handle what the authors call reflexive management, i.e., the ability to manage dependable systems.
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 2026-10-12. 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.