Natural Language Processing and Information Systems

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.

Klappentext

.- Short papers (Main Track). .- Exploration of Rationale-Extraction Methods for Closed-Domain Question Answering with a New Sentence-Level Rationale Dataset. .- Hybrid-SET: Few-shot Example Selection Combining Sentence Similarity and Set Coverage - A Case Study on Material Science Domain. .- Efficiently Summarizing Norwegian Legal Texts. .- FairNM: Fairness in Name Matching. .- Is a Similar Task Useful for Few-Shot Selection? Aspect Term Extraction Using LLM. .- IRIS: Rapid Curation Framework for Iterative Improvement of Noisy Named Entity Annotations. .- Fusion-in-LLM: A Parallel Approach to Improve Retrieval-Augmented Generation for Quiz-Based Question Answering. .- Unveiling Emotional Signature in Conspiracy Topics on Social Media through Vector Analysis. .- LLM-Supervised Multilingual Skill Extraction and Classification from Job Ads. .- Cross-Domain Named Entity Recognition: A Resource-Efficient Transfer Learning Approach. .- Explainable AI for NLP: Enhancing Transparency in Sentiment Analysis and Named Entity Recognition. .- Utilization of SLMs as Generator in RAG. .- Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study. .- Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications. .- EcoRAG: A Multi-Hop Economic QA Benchmark for Retrieval Augmented Generation Using Knowledge Graphs. .- Short papers (Industry Track). .- Should Embedding-Based News Recommendation Be Revisited? A Focus on the Differences Between News Publishers and Aggregators. .- A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification. .- Testing Procedure Generation based on Testing requirements for Automotive Components with LLM fine-tuning. .- OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model. .- Demo papers. .- ESG-Consultant: Developing of an ESG Compliance Consulting Tool for Companies Using RAG. .- CaLuX: A Catalyst and Lubricant Properties Extraction System for Domain Experts.

Inhalt

.- Short papers (Main Track).

.- Exploration of Rationale-Extraction Methods for Closed-Domain Question Answering with a New Sentence-Level Rationale Dataset.

.- Hybrid-SET: Few-shot Example Selection Combining Sentence Similarity and Set Coverage - A Case Study on Material Science Domain.

.- Efficiently Summarizing Norwegian Legal Texts.

.- FairNM: Fairness in Name Matching.

.- Is a Similar Task Useful for Few-Shot Selection? Aspect Term Extraction Using LLM.

.- IRIS: Rapid Curation Framework for Iterative Improvement of Noisy Named Entity Annotations.

.- Fusion-in-LLM: A Parallel Approach to Improve Retrieval-Augmented Generation for Quiz-Based Question Answering.

.- Unveiling Emotional Signature in Conspiracy Topics on Social Media through Vector Analysis.

.- LLM-Supervised Multilingual Skill Extraction and Classification from Job Ads.

.- Cross-Domain Named Entity Recognition: A Resource-Efficient Transfer Learning Approach.

.- Explainable AI for NLP: Enhancing Transparency in Sentiment Analysis and Named Entity Recognition.

.- Utilization of SLMs as Generator in RAG.

.- Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study.

.- Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications.

.- EcoRAG: A Multi-Hop Economic QA Benchmark for Retrieval Augmented Generation Using Knowledge Graphs.

.- Short papers (Industry Track).

.- Should Embedding-Based News Recommendation Be Revisited? A Focus on the Differences Between News Publishers and Aggregators.

.- A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification.

.- Testing Procedure Generation based on Testing requirements for Automotive Components with LLM fine-tuning.

.- OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model.

.- Demo papers.

.- ESG-Consultant: Developing of an ESG Compliance Consulting Tool for Companies Using RAG.

.- CaLuX: A Catalyst and Lubricant Properties Extraction System for Domain Experts.