large language models

Adaptive Self-Selection and Collaborative Selection in Self-and-Other Models: A General Framework for Dynamic Selection-Mode Switching

Selection is a fundamental operation in intelligent systems, computational systems, optimization processes, and model-based reasoning. Existing approaches commonly rely on independent selection, centralized decision-making, voting, ranking, or collaborative selection mechanisms. However, a system that consistently uses...

Application of LLM combined with knowledge base in improving C-TIRADS grading of thyroid nodules

Objective This study used the unified text-based grading results of senior sonographers as the primary reference (this text benchmark is not pathological diagnostic gold standard) to evaluate the concordance of text-derived C-TIRADS grades assigned by six large language models (LLMs), with and without FastGPT Retrieval...

Ontology-Enriched GraphRAG: A Case Study in Portuguese Geoscience Question Answering

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs) in Question-Answering (QA) tasks. However, traditional text-based retrieval may prove insufficient in specialized domains, such as geoscience, where critical information is highly interconnected and distributed across complex conce...

The Economics of Orchestration: Can Culturally-Composed Teams of Small Language Models Outperform Frontier Models at Equal Cost? A Cost-Matched Experiment on Business Solution Generation — Reproducibility Package

Reproducibility package for the paper 'The Economics of Orchestration'. Organizations deploying large language models face a budget choice: pay for a frontier model, or orchestrate cheaper models into a multi-step pipeline. Across three pre-registered studies (a 2x2x2 factorial over five LLM families and 19 business pr...

Adaptive Self–Mutual Correction Between Self-and-Interactive Models: A General Framework for Error Detection, Correction, and Mode Switching

Correction is a fundamental requirement for intelligent systems that must maintain consistency, adapt to changing environments, and improve their internal representations. Existing approaches investigate error correction through self-correction, feedback control, iterative refinement, peer interaction, distributed syst...

A Computational Swinging Lexical Network: Cohort Concentration Predicts Semantic Interference in a Large-Scale Picture–Word Interference Dataset

The Swinging Lexical Network (SLN) model explains semantic context effects in word production through the lexical cohort that a target and distractor co-activate: whether naming is facilitated or slowed depends on the balance between semantic priming and lexical competition within this cohort. As a verbal theory the SL...

Development and Exploratory Evaluation of a Large Language Model-Supported Scoping Review Workflow

From Dyadic Reciprocity to Giant Interaction Engines

In this paper, based on posthumanist theory and posthumanist linguistics, we discuss specific elaborations of the term interaction as found in linguistics and sociology, where interactivity, reciprocal awareness and agency are discussed as possible characteristics of human interaction. We problematise to what extent th...

Mapping Carbon-Based Sustainability Research Using a Customized BERTopic Framework with TF-IDF–LSA Document Representations

This study examines the thematic structure and temporal development of carbon-based sustainability research using a customized BERTopic framework based on TF-IDF–LSA document representations. Covering the period between 2020 and 2026, the study analyzes 58,307 cleaned bibliographic records retrieved from Scopus. Of the...

World Self-and-Mutual Models: Adaptive Switching Between Self-Diagnosis and Mutual Diagnosis for World-State Understanding and Model Reliability

World models provide computational representations of environmental states, transitions, and potential outcomes. However, a world model may contain internal inconsistencies, inaccurate state estimates, incorrect transition predictions, or assumptions that no longer correspond to the environment. Diagnosing these proble...

Classical Tricks for Better Topics: Can Traditional Text Mining Techniques Improve Generative Topic Modeling?

Topic modeling is widely used to discover and organize latent themes in large text collections. While recent embedding-based methods have improved topic discovery by leveraging dense semantic representations, they typically represent topics as lists of keywords, often providing limited insights into the underlying them...

Adaptive Self-Play and Multi-Model Play in Self-and-Interaction Models: A Unified Framework for Dynamic Switching Between Internal and Inter-Model Strategic Exploration

Self-play and multi-model interaction provide different mechanisms for exploring complex problem spaces. Self-play enables a model to generate, evaluate, and challenge its own strategic alternatives, whereas multi-model play enables multiple models to interact through competition, cooperation, adversarial examination,...