The two-volume set LNCS 15836 and 15837 constitutes the proceedings of the 30th International Conference on Applications of Natural Language to Information Systems, NLDB 2025, held in Kanazawa, Japan, during July 46, 2025.
The 33 full papers, 19 short papers and 2 demo papers presented in this volume were carefully reviewed and selected from 120 submissions. The proceedings contain novel and significant research contributions addressing theoretical aspects, algorithms, applications, architectures, resources, and other aspects of NLP, as well as survey and discussion papers.
.- Full papers (Main Track).
.- Multi-Scale Convolutional Fusion with Contrastive Feature Alignment for
Imbalanced Data Classification.
.- Memory Efficient LM Compression using Fisher Information from Low-Rank
Representations.
.- Accelerating End-to-End PDF to Markdown Conversion through Assisted
Generation.
.- Comparison of pipelines, seq2seq models, and LLMs for rare
disease information extraction.
.- Multiple Graphical Convolution Networks Approach for
Aspect-Based Sentiment Classification.
.- How important is domain-specific language model pretraining
and instruction finetuning for biomedical relation extraction?.
.- ShortPathQA: A Dataset for Controllable Fusion of Large Language Models
with Knowledge Graphs.
.- Explaining Bias in Internal Representations of Large Language Models via
Concept Activation Vectors.
.- Duplicate Bug Report Retrieval for New Bug Reports.
.- Context Is The Key For LLM-Based Text Segmentation.
.- MultiProSE: A Multi-label Arabic Dataset for Propaganda, Sentiment, and
Emotion Detection.
.- CLIP-Driven Deep Hashing for Cross-Modal Retrieval.
.- WIP: Iterative Post-Training Pruning with Weighted Importance Estimation
for Large Language Models.
.- A Comparative Study on the Development of a Thai Legal QA Framework Using
Large Language Models and Mixed Legal Datasets.
.- Leveraging Generative AI for Chronic Kidney Disease Prediction:
A Comparative Study of Open-Source LLMs.
.- LADDER: Latent Attention and Decomposition for Deep Enhanced Retrieval in
Medical Question-Answering Systems.
.- Test It Before You Trust It: Applying Software Testing for
Trustworthy In-context Learning.
.- CAFE: Context-aware Applicability-weighted Fairness Evaluation.
.- A Survey of LoRA Algorithm Variations for Language Models.
.- ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness
Prediction via Human-AI Collaborative Annotation.
.-Towards an Ontological Approach to Browser Fingerprinting Detection and
Privacy Risk Assessment.
.- Dual-Style Transcription of Historical Manuscripts based on
Multimodal Small Language Models with Switchable Adapters.
.- Semantic Reasoning for Device Identification in Dynamic Internet of Things
Environments with Large Language Model.
.- Instruction Tuning TextFlow Semi-Automatic RFCs Generation.
.- News Timeline Summarization: Recent Methods.
.- QA2HALL: A Framework for Generating Non-trivial Hallucination Detection
Datasets from KGQA Datasets.
.- Causal Relation-Aware Data Augmentation for Legal Textual Entailment.
.- Improve Smart Contract Vulnerability Explanation with Synthetic Data and
Chain-of-Thought Prompting.
.- The benefits of query-based KGQA systems for complex and
temporal questions in LLM era.
.- TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine
Translation for Documentaries.
.- Multimodal Event Detection: Current Approaches and Defining the New
Playground through LLMs and VLMs.
.- ReSHQ: Re-ranking Based on the Similarity between Hypothetical Query and
Query.
.- Multi-hop Question Answering in SlideVQA Based on Beam Retrieval.
