Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented GenerationiFlytek · Annual Meeting of the Association for Computational Linguistics (ACL)3 citationsJan 1, 2025From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question GenerationiFlytek · Annual Meeting of the Association for Computational Linguistics (ACL)3 citationsJan 1, 2025Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention LearningiFlytek · Annual Meeting of the Association for Computational Linguistics (ACL)3 citationsJan 1, 2025Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced OptimizationiFlytek · Annual Meeting of the Association for Computational Linguistics (ACL)2 citationsJan 1, 2025Chain of Strategy Optimization Makes Large Language Models Better Emotional SupporteriFlytek · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)1 citationJan 1, 2025FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text TrainingiFlytek · neural information processing systemsJan 1, 2025Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation LearningiFlytek · neural information processing systemsJan 1, 2025Exploration and Practice of the "Industry-Education Integration · Four-Stage Progressive" Talent Training Model for Applied Artificial Intelligence ProfessionalsiFlytek · Entrepreneurship and InnovationJan 1, 2025Scalable Data Synthesis through Human-like Cognitive Imitation and Data RecombinationiFlytek · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential AnalysisiFlytek · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code GenerationiFlytek · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities DegradationiFlytek · neural information processing systemsJan 1, 2025You Might Not Need Attention DiagonalsiFlytek · IEEE Signal Processing LettersJan 1, 2025Attention-Guided Contrastive Masked Autoencoders for Self-supervised Cross-Modal Biometric MatchingiFlytek · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications EngineeringJan 1, 2025