SmaLLEXT 2025
Small and Efficient Large Language Models for Knowledge Extraction 2025

Table of Contents

• Preface
  Summary: There were 7 papers submitted for peer review to this workshop. Out of these, 5 papers were accepted as peer-reviewed papers for this volume.
  1-5

Peer-reviewed papers

• Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models
  Antonio Colacicco, Vito Guida, Dario Di Palma, Fedelucio Narducci, Tommaso Di Noia
  6-14
• Exploiting LLMs to Improve Recommendation Diversity
  Basar Yilmaz, Ali Eren Cankaya, Ismail Sengor Altingovde, Pinar Karagoz, Ismail Hakki Toroslu
  15-24
• SEDA: A Self-Adapted Entity-Centric Data Augmentation for Boosting Grid-based Discontinuous NER Models
  Wen-Fang Su, Hsiao-Wei Chou, Wen-Yang Lin
  25-39
• CliqueParcel: An Approach for Batching LLM Prompts that Jointly Optimizes Efficiency and Faithfulness
  Jiayi Liu, Tinghan Yang, Jennifer Neville
  40-58
• Identifying Business Trends from Stock Market Data utilizing Domain-Specialized Sentence-RoBERTa and BERTopic Technique
  Ye Lim Jung, Hyoung Sun Yoo
  59-64

Keynotes

• Automating Neural Network Design: Neural Architecture Search for Small and Efficient Models - Keynote
  Aaron Klein
  65-69
• Machine Learning Without Data: Training Small Expert Agents With Minimal Examples - Keynote
  Jacek Golebiowski, Maciej Gryka, Vineeth Reddy Guda, Gabi Kadlecová, Bartek Kruszczyński, Selim Nowicki, Jonas Verschueren, Usman Zafar
  70-77