Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
How Far Are We From AGI: Are LLMs All We Need?
Authors: Tao Feng, Chuanyang Jin, Jingyu Liu, Kunlun Zhu, Haoqin Tu, Zirui Cheng, Guanyu Lin, Jiaxuan You
TMLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Unlike previous survey papers, this work goes beyond summarizing LLMs by addressing key questions about our progress toward AGI and outlining the strategies essential for its realization through comprehensive analysis, in-depth discussions, and novel insights. |
| Researcher Affiliation | Academia | 1University of Illinois Urbana-Champaign 2Johns Hopkins University 3University of Chicago 4University of California, Santa Cruz 5Carnegie Mellon University |
| Pseudocode | No | The paper is a comprehensive survey and does not present any novel algorithms or procedures in pseudocode blocks. |
| Open Source Code | Yes | 1Project website: https://github.com/ulab-uiuc/AGI-survey. Unlike traditional publications that remain static, we embrace an innovative approach by treating this paper as a living document. We warmly welcome feedback from the community and plan to update the paper annually. Contributors on the project website will be gratefully acknowledged in future revisions. |
| Open Datasets | No | The paper is a survey and does not present new experimental results based on a specific dataset. It discusses many existing datasets in the context of other research, but no dataset is used for experiments conducted by the authors of this paper. |
| Dataset Splits | No | The paper is a survey and does not conduct experiments with specific datasets, therefore it does not provide dataset splits. |
| Hardware Specification | No | The paper is a survey and does not conduct experiments, therefore it does not specify hardware used for running experiments. |
| Software Dependencies | No | The paper is a survey and does not conduct experiments, therefore it does not specify software dependencies with version numbers. |
| Experiment Setup | No | The paper is a survey and does not conduct original experiments, therefore it does not provide an experimental setup with hyperparameter values or training configurations. |