Position: Key Claims in LLM Research Have a Long Tail of Footnotes

Authors: Anna Rogers, Sasha Luccioni

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This position paper argues that LLM research should be more precise with its key terms and claims.
Researcher Affiliation Collaboration 1IT University of Copenhagen 2Hugging Face, Canada. Correspondence to: Anna Rogers <arog@itu.dk>, Sasha Luccioni <sasha.luccioni@hf.co>.
Pseudocode No No, the paper is a position paper and does not include any pseudocode or algorithm blocks.
Open Source Code No No, the paper is a position paper and does not describe a new methodology for which open-source code would be provided.
Open Datasets No No, this is a position paper and does not involve training models on a dataset. It discusses concepts and critiques claims within LLM research rather than presenting new experimental data.
Dataset Splits No No, this paper is a position paper and does not describe experiments that would involve dataset splits for validation.
Hardware Specification No No, the paper is a position paper and does not conduct experiments requiring specific hardware specifications.
Software Dependencies No No, the paper is a position paper and does not conduct experiments requiring specific software dependencies.
Experiment Setup No No, the paper is a position paper and does not describe an experimental setup with hyperparameters or system-level training settings.