Résultats de recherche pour « Large Language Model »

Introdução: A utilização de dados de saúde em pesquisas é limitada por questões éticas. Isso desafia os pesquisadores a encontrarem formas de obter o material necessário para desenvolverem seu trabalho. Método: Usou-se uma ferramenta de Large Language Model (LLM) para gerar prontuários eletrônicos (PE) sintéticos de pacientes cardiológicos utilizando-se as técnicas "few-shot prompting" e "chain-of-thought prompting". Objetivo: criar um conjunto de dados abrangente e acessível para auxiliar no treinamento de algoritmos de classificação de texto em cenários médicos. Resultados: Foram gerados 103 PE sintéticos, abrangendo diagnósticos cardíacos distintos. Conclusão: A geração de PE sintéticos através de LLM apresentaram qualidade esperada, sendo condizentes com o conteúdo encontrado em PE reais. O conjunto de dados está disponível no repositório Zenodo para uso irrestrito pela comunidade de pesquisa, seguindo o conceito de ciência aberta.

Large language models (LLMs) have become ubiquitous tools across numerous domains such as education, healthcare, and professional advisory services. However, their susceptibility to sycophancy-a bias toward echoing user prompts over independently reasoning-poses a critical threat to model reliability. We present a Bayesian-latent variable framework that introduces a hidden sycophancy score Si,m,u,p ∼ N (0, σ 2 S) to quantify such behavior. The framework defines a flip indicator ∆i,m,u,p ∈ {−1, 0, +1} to distinguish regressive (accuracydecreasing) from progressive (accuracy-increasing) shifts. Our generative logistic model ties correctness probabilities to latent agreement pressure via Pr(ŷ (1) = 1) = σ(x ⊤ β + γmSi,m,u,p), enabling rigorous posterior inference. Empirically, we find an average sycophancy-induced shift of E[|S|] ≈ 0.8σS, and a model susceptibility factor γ that directly controls response volatility. Simulated results show that nearly 50% of responses flip under user cues, with regressive flips dominating when γ < 0. Our approach provides a statistically grounded diagnostic for auditing and improving trustworthiness in LLM behavior under social influence. Simulation code for this study is available at: https://github.com/ParthaPRay/Sycophancy_in_LLM_model.

Abstract There are already many DNA large language models, but most of them still follow traditional uses, such as extracting sequence features for classification tasks. More innovative applications of large language models, such as prompt engineering, RAG, and zero-shot or few-shot prediction, remain challenging for DNA-based models. The key issue lies in the fact that DNA models and human natural language models are entirely separate; however, techniques like prompt engineering require the use of natural language, thereby significantly limiting the application of DNA large language models. This paper introduces a pre-trained model trained on the GPT-2 network, combining DNA sequences and English text, and uses a unified BPE tokenization method. We then convert classification and other downstream tasks into Alpaca format instruction data, and perform instruction fine-tuning on this pre-trained model to create a fine-tuned model capable of handling multiple tasks. The model has demonstrated its effectiveness in DNA related zero-shot prediction and multitask application. This research provides a highly promising direction for building a unified DNA sequence task framework.

In the standard transformer architecture, in creasing model parameters leads to linear growth in computational cost and activation memory. To address this issue, we propose a novel Infinite Parameter Large Language Model (IP-LLM) architecture that decouples model size from computational cost and de vice memory. Existing large language models Figure 1: Parameters A, B, C, and D store knowledge are all fixed-parameter models, while human knowledge is infinite and expands daily. Finite parameters are inherently limited in their capac ity to accommodate this boundless knowledge. Our IP-LLM architecture can potentially ac commodate infinite knowledge, resolving this issue and laying the foundation for realizing a truly omniscient and omnipotent artificial gen eral intelligence in the future.Our architecture surpasses MOE in performance while requiring significantly less memory.