Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Teaching Language Models to Reason with ToolsAlibaba · neural information processing systemsJan 1, 2025MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?Alibaba · neural information processing systemsJan 1, 2025TokenSqueeze: Performance-Preserving Compression for Reasoning LLMsAlibaba · neural information processing systemsJan 1, 2025Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement LearningAlibaba · neural information processing systemsJan 1, 2025FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language ModelsAlibaba · neural information processing systemsJan 1, 2025GSID: Generative Semantic Indexing for E-Commerce Product UnderstandingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025Advancing E-commerce Merchants Telemarketing with Synthetic Data-Driven LLMsAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge DistillationAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMsAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025SEAL: Structure and Element Aware Learning Improves Long Structured Document RetrievalAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025DecoupleSearch: Decouple Planning and Search via Hierarchical Reward ModelingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025CoEvo: Coevolution of LLM and Retrieval Model for Domain-Specific Information RetrievalAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy OptimizationAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025Advancing Reasoning with Off-the-Shelf LLMs: A Semantic Structure PerspectiveAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding CompressionAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language ModelsAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document UnderstandingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based InferenceAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation BenchmarkingAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-PlayingAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer SynthesisAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025ChartM3: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart ComprehensionAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language ModelsAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout GroundingAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025EoT: Evolution of Thoughts for Complex Reasoning TasksAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025