Read more
The four-volume set LNAI 16102 - 16105 constitutes the refereed proceedings of the 14th CCF National Conference on Natural Language Processing and Chinese Computing, NLPCC 2025, held in Urumqi, China, during August 7 9, 2025.
The 152 full papers and 26 evaluation workshop papers included in these proceedings were carefully reviewed and selected from 505 submissions. They were focused on the following topical sections:
Part I : Information Extraction and Knowledge Graph & Large Language Models and Agents.
Part II : Multimodality and Explainability & NLP Applications / Text Mining.
Part III : IR / Dialogue Systems / Question Answering; Machine Translation and Multilinguality & Sentiment analysis / Argumentation Mining / Social Media.
Part IV : Machine Learning for NLP; Fundamentals of NLP; Summarization and Generation; Others &
Evaluation Workshop.
List of contents
.- Multimodality and Explainability.
.- DPIMerge: An Efficient Dynamic Parameter Interpolation Framework for Alleviating Pure Text Forgetting in Multimodal Large Models.
.- MRF: A Modality-Resilient Framework for Handling Missing Modalities in Multimodal Learning.
.- StoryBench: A Dataset for Diverse, Explainable, Multi-hop Narrative Text-to-Image Generation.
.- Mitigating Object Hallucination through Assembled Chain-of-Thought Reasoning.
.- DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities.
.- Bi-directional Semantic Alignment for Large Vision Language Model Training via Echo-Former.
.- A Southeast Asian Language OCR Dataset and Evaluation for Large Multimodal Models.
.- DiagDiff: A Diagnosis-Aware Diffusion Model for Radiology Report Generation.
.- Fine-grained prosody-controllable Lao speech synthesis guided by natural language.
.- How Do Shared Experts Dynamically Adapt to Routing Constraints in Mixture-of-Experts?.
.- End-to-End VideoQA with Frame Scoring Mechanisms and Adaptive Sampling.
.- Visual Sketchbook: Enhancing Chart-to-Code Generation via Reflective Refinement.
.- Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models.
.- Gradient Co-occurrence Analysis for Detecting Unsafe Prompts in Large Language Models.
.- NLP Applications / Text Mining.
.- Enhancing Coherence Measurement based on Rhetorical Structure Theory for AES Task.
.- Enhancing GPT-based Input Method with Domain-Adaptive Pinyin Encoder(s).
.- Improving Grammatical Error Correction with Dynamic Linguistic Knowledge Fusion.
.- SAGEC: Syntax-Aware Grammatical Error Correction with Retrieval-Augmented Generation.
.- DRA: A Dual Retrieval Architecture for Domain Chinese Spelling Check.
.- Label-Guided Self-Knowledge Distillation for Multi-class Text Classification.
.- MvDDI: A Multi-view Interaction Framework for Few-shot Drug-Drug Interaction.
.- MQA-SQL: Mitigating Question Ambiguity in Text-to-SQL with Multi-Model Collaboration and Multi-Variant Query Rephrasing.
.- Dialogue-Based Multi-Dimensional Relationship Extraction from Novels.
.- RAG-targeted SFT Improves RAG-enhanced Math Reasoning.
.- Linguistic Error-aware Data Augmentation for Lao Grammatical Error
Correction.
.- LyRE:Learning Varying Fusion Degrees with Hierarchical Aggregation to Improve Multimodal Misinformation Detection.
.- FTAF: Facilitating Fine-grained Toxic Language Detection via Text Rewriting and Relationship Chain Learning.
.- CLSurCoder: LLMs based Cross-Lingual Transfer Learning for Low-resource Language Surgical Records Coding.
.- CPO-SQL: Boosting Small LLMs for Text-to-SQL via Efficient In-Context Learning and Preference Optimization.
.- Structured Topic-Enhanced News Recommendation Method with Multi-View Learning.
.- Identity-Driven Hierarchical Role-Playing Agents.
.- MoSGCN: Aspect-based sentiment analysis via distance matrix and similarity graph.
.- Two Steps to Precision: Enhancing Reliable API Invocation in Code Generation.
.- FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios.
.- Open Bilingual Benchmark and Leaderboard for Large Language Models in Cybersecurity.
.- LLMA4ITOps: A Lightweight LLM-based Multi-Agent Framework for IT Operations and Maintenance.
.- Genre-Wise Graph Representations for Multi-Trait Essay Scoring.
.- Automatic Evaluating Scientific Reviews through Meta-Reviewer s Lens: A Reliable Benchmark for Peer Review Generation.
.- Control Extreme Multi-Label Generation via Level-Guided Token Filtering.
.- Astronomical Catalogue Recommendation Based on Graph Neural Networks.
Summary
The four-volume set LNAI 16102 - 16105 constitutes the refereed proceedings of the 14th CCF National Conference on Natural Language Processing and Chinese Computing, NLPCC 2025, held in Urumqi, China, during August 7–9, 2025.
The 152 full papers and 26 evaluation workshop papers included in these proceedings were carefully reviewed and selected from 505 submissions. They were focused on the following topical sections:
Part I : Information Extraction and Knowledge Graph & Large Language Models and Agents.
Part II : Multimodality and Explainability & NLP Applications / Text Mining.
Part III : IR / Dialogue Systems / Question Answering; Machine Translation and Multilinguality & Sentiment analysis / Argumentation Mining / Social Media.
Part IV : Machine Learning for NLP; Fundamentals of NLP; Summarization and Generation; Others &
Evaluation Workshop.
