large language models

The Model-Infrastructure Co-Evolution in Conversational NLU: From ELIZA to Large Language Models

Conversational Natural Language Understanding (NLU) has passed through five distinguishable technological eras: rule-based symbolic parsing, statistical and probabilistic modelling, neural sequence learning, Transformer-based pretraining, and the current large language model regime. Existing accounts of this history te...

Evaluating LLM-Generated Conceptual Models: A Theoretical Approach for Formalizing the Calculation of Metrics on the Meta Level

Multi-Crop Leaf Disease Detection with LLM-Assisted Diagnosis and Explainable AI

Early identification of plant diseases is crucial for maintaining agricultural productivity and ensuring food security.Manually inspecting crop leaves takes a lot of time and requires expertise, making automated disease detection systems very helpful.This paper presents a framework for detecting leaf diseases in multip...

Transl-AI-tion 2.0

Artificial intelligence (AI) is transforming translation and interpreting with unprecedented speed, raising fundamental questions about the future of cross-lingual communication. This edited volume brings together scholars and practitioners from around the world to examine the technological, ethical, legal and pedagogi...

Proficiency informed knowledge tracing: Leveraging large language models to enhance predictive methods in mathematics learning

Predictive methods play a key role in learning systems to enable effective interventions. However, most existing approaches emphasize concept-level suggestions and pay limited attention to cognitive constructs aligned with instructional goals. For instance, in mathematics, mastery depends on the integrated and balanced...

Comparing large language models and prompting techniques to control an embodied persuasive coach

Embodied agents play a crucial role in applications designed to influence user behaviour. Traditionally, crafting these agents requires considerable human effort. Large Language Models (LLMs) might open the possibility of creating agents capable of autonomous, open-ended interactions without labour-intensive developmen...

A Multi-stage Hybrid Retrieval Framework for Knowledge-Augmented Question Answering

AI Agents for CRISPR Diagnostics: From Automation to Bounded Autonomy

Recent years have witnessed rapid advances in clustered regularly interspaced short palindromic repeats (CRISPR) diagnostics, artificial intelligence (AI), and self-driving laboratories for automation. CRISPR diagnostics have emerged as a promising strategy for earlier disease detection, with Cas12a and Cas13a targetin...

DRoG: Distance-Aware Retrieval and Dual-Role Reasoning on Graphs for Large Language Models

ReVerTree: Recursive Verification Tree for Self-checking Mathematical Reasoning

Assessing Graph Data Serialization and Context Selection for Knowledge-Augmented Question Answering with Large Language Models

Large language models (LLMs) can produce inaccurate answers even when relevant facts are supplied in the prompt. This study examines how graph data serialization, entity identifiers, and context selection affect factual question answering in knowledge-augmented prompting. Four synthetic knowledge graph datasets contain...

Experiments with Template-Based SPARQL Generation from Natural Language Questions