cover

Supplementary Figures and Supplementary Tables

16 Dec 2024

cover

LLMs Rely on Contextual Knowledge Over Background Knowledge

16 Dec 2024

LLMs rely on contextual knowledge over domain-specific facts, maintaining accuracy even with synthetic gene names in reasoning tasks.

cover

How Extra Information Affects AI’s Ability to Think Logically

16 Dec 2024

LLMs demonstrate varying sensitivity to increasing distractors in reasoning tasks.

cover

Misalignment Between Instructions and Responses in Domain-Specific LLM Tasks

15 Dec 2024

Analysis of domain-specific LLM responses reveals issues like empty outputs, incorrect or repeated content, and misaligned Chain-of-Thought (CoT) reasoning.

cover

Few-shot Prompting for Logical Reasoning Tasks in Biological Pathways

15 Dec 2024

Explore few-shot prompting techniques for logical reasoning tasks in biological pathways.

cover

Zero-shot Prompts for Logical Reasoning Tasks in Biological Pathways

14 Dec 2024

Explore zero-shot prompting techniques for logical reasoning tasks related to signaling and metabolic molecules in biological pathways.

cover

Evaluation Metrics for Assessing LLM Performance on Syllogistic Tasks

14 Dec 2024

Evaluation metrics for LLM performance include accuracy, F1-score, recall, reasoning accuracy, and faithfulness, ensuring meaningful and compliant responses.

cover

Experimental Setup for Evaluating LLM Performance on Biomedical Syllogistic Tasks

13 Dec 2024

Overview of the experimental setup for evaluating LLMs on syllogistic tasks, including modules, parameters, and computational resources used.

cover

Accessing and Utilizing Pretrained LLMs: A Guide to Mistral AI and Other Open-Source Models"

13 Dec 2024

Learn how to access and utilize pretrained LLMs such as Mistral-7B and BioMistral for advanced natural language processing tasks.