Common Sense: the Dark Matter of Language and Intelligence (VLDB 2023 Keynote)
Summary: Argues that commonsense knowledge is the “dark matter” missing from scale-driven LLMs, producing brittle, nonsensical errors. Demonstrates that smaller academic models can outperform giant models when augmented with explicit commonsense knowledge and inference‑time reasoning. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yejin Choi (Allen Institute; University of Washington)
BibTeX Citation
@article{choi_vldb23,
title = {{Common Sense: the Dark Matter of Language and Intelligence (VLDB 2023 Keynote)}},
author = {Choi, Yejin},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {12},
pages = {4139--4139},
doi = {10.14778/3611540.3611638},
url = {https://doi.org/10.14778/3611540.3611638},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,483 | Are Large Language Models a Good Replacement of Taxonomies? | 2024 | VLDB | 5.6074551e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 13,296 | How to Build a Brain | 2025 | SIGMOD |
| 2 | 13,480 | Systems and ML: When the Sum is Greater than Its Parts | 2020 | SIGMOD |
| 3 | 13,376 | Sharing Information with Differential Privacy: A Database Perspective (VLDB 2024 Keynote) | 2024 | VLDB |
| 4 | 13,352 | The Limitations of Data, Machine Learning and Us | 2024 | SIGMOD |
| 5 | 8,018 | The Journey to A Knowledgeable Assistant with Retrieval-Augmented Generation (RAG) | 2024 | SIGMOD |
| 6 | 6,945 | Building Machine Learning Systems that Understand | 2016 | SIGMOD |
| 7 | 13,470 | From ML Models to Intelligent Applications: The Rise of MLOps | 2021 | VLDB |
| 8 | 14,400 | Computers versus Common Sense | 1991 | SIGMOD |
| 9 | 13,400 | Will LLMs reshape, supercharge, or kill data science? (VLDB 2023 Panel) | 2023 | VLDB |
| 10 | 13,377 | Harmonizing ML and Databases: A Symphony of Data (VLDB 2024 Keynote) | 2024 | VLDB |