Mualla / Yu / Liga Advances in Explainability, Agents, and Large Language Models

First International Workshop on Causality, Agents and Large Models, CALM 2024, Kyoto, Japan, November 18–19, 2024, Proceedings
Erscheinungsjahr 2025
ISBN: 978-3-031-89103-8
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 127 Seiten

Reihe: Communications in Computer and Information Science

This book constitutes the refereed proceedings of the First International Workshop on Advances in explainability, agents, and large language models, CALM 2024, held in Kyoto, Japan, during November 18–19, 2024.

The 7 full papers and 1 short paper presented in this book were carefully reviewed and selected from 17 submissions. The Workshop on Causality, Agents, and Large Models (CALM) was established to foster interdisciplinary collaboration and advance research at the intersection of causal reasoning, multi-agent systems (MAS), and large language models (LLMs).

Zielgruppe

Research

Autoren/Hrsg.

Mualla, Yazan

Yu, Liuwen

Liga, Davide

Tchappi, Igor

Markovich, Réka

Inhaltsverzeichnis

.- Enhancing Personalized Nutrition: A Hybrid Intelligence Approach with LLM-Powered Meal Planning.

.- Generating Explanations for Molecular Property Predictions in Graph Neural Networks.

.- Balancing (Normative) Reasons for the Intelligent Human-input-based Blockchain Oracle.

.- Feature Generation Using LLMs: An Evolutionary Algorithm Approach.

.- Augmenting Dark Patterns Text Data by Leveraging Large Language Models: a Multi-Agent Framework and Parameter-Efficient Fine-Tuning.

.- Assessing the Robustness of LLMs in Predicting Supports and Attacks.

.- Enhancing accuracy and explainability in anomaly classification with large language models.

.- Agent-Based Hate Speech Moderation Approach.