Minimizing Factual Inconsistency And Hallucination In Large Language Models

November 2023 in “ ArXiv.org ”

I Muneeswaran, Shreya Saxena, Siva Prasad, M. Prakash, Advaith Shankar, V Varun, Vishal Vaddina, Saisubramaniam Gopalakrishnan

Studysummary This study demonstrates that a proposed multi-stage framework improves the accuracy and faithfulness of drug-related responses generated by language models, compared to traditional methods.

Our plain-language summary. Not medical advice or a treatment recommendation. Consult a qualified healthcare professional before changing treatment. Full disclaimer ·

View this study on arxiv.org →

Discuss this study in the Community →

Similar Research

5 / 1000+ results

research Medical Reasoning with Large Language Models: A Survey and MR-Bench

March 2026 in “ArXiv.org”

This review presents a comprehensive evaluation of medical reasoning using large language models, highlighting a significant gap between exam-level performance and true clinical decision-making accuracy.

research Towards Fairer Health Recommendations: finding informative unbiased samples via Word Sense Disambiguation

September 2024 in “arXiv (Cornell University)”

This study evaluated various NLP models for detecting bias in medical curricula, finding that fine-tuned BERT models perform well, whereas LLMs, despite being state-of-the-art in many tasks, are unsuitable for this application.

research Evaluating anti-LGBTQIA+ medical bias in large language models

1 citations , September 2025 in “PLOS Digital Health”

This study found that all four evaluated large language models generated a significant proportion of inappropriate responses when prompted with or without LGBTQIA+ identity terms, with more severe bias observed in prompts mentioning LGBTQIA+ identities.

The Dark Side of the Language: Syntax-Based Neural Networks Rivaling Transformers in Unseen Sentences

research The Dark Side of the Language: Syntax-Based Neural Networks Rivaling Transformers in Definitely Unseen Sentences

1 citations , October 2023

In this study, the authors found that syntax-based neural networks performed comparably to pre-trained Transformers on tasks involving definitely unseen sentences, suggesting they are a more transparent and parameter-efficient alternative for certain Natural Language Processing applications.

research Publicly Available Large Language Models for Trichoscopy: A Head-to-Head Comparison with Dermatologists

January 2026 in “Diagnostics”

This study reports that publicly available large language models are currently less accurate than human experts in diagnosing trichoscopic images, suggesting the need for further development and specialized training for these AI tools in trichology.