Upgrade to Pro — share decks privately, control downloads, hide ads and more …

[WIP] How Do Large Language Models Acquire Fact...

Avatar for Yano Yano
August 23, 2025
0
8

[WIP] How Do Large Language Models Acquire Factual Knowledge During Pretraining?

Avatar for Yano

Yano

August 23, 2025
Tweet

More Decks by Yano

See All by Yano
NLP2025参加報告
Avatar for Yano yano0
0
530
【輪講資料】ReAct: Synergizing Reasoning and Acting in Language Models / Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Avatar for Yano yano0
0
170
【輪講資料】SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
Avatar for Yano yano0
2
320
【輪講資料】From Zero to Hero: On the Limitations of Zero-Shot Language Transfer with Multilingual Transformers
Avatar for Yano yano0
0
84
【輪講資料】Zero-shot Cross-lingual Semantic Parsing
Avatar for Yano yano0
0
120

Featured

See All Featured
Let's Do A Bunch of Simple Stuff to Make Websites Faster
Avatar for Chris Coyier chriscoyier
507
140k
The World Runs on Bad Software
Avatar for Brandon Keepers bkeepers
PRO
70
11k
Writing Fast Ruby
Avatar for Erik Berlin sferik
628
62k
Art, The Web, and Tiny UX
Avatar for Lynn Fisher lynnandtonic
302
21k
Build your cross-platform service in a week with App Engine
Avatar for Jose L jlugia
231
18k
YesSQL, Process and Tooling at Scale
Avatar for Rocio Delgado rocio
173
14k
The Success of Rails: Ensuring Growth for the Next 100 Years
Avatar for Eileen M. Uchitelle eileencodes
46
7.6k
Agile that works and the tools we love
Avatar for Rasmus Luckow-Nielsen rasmusluckow
329
21k
A Modern Web Designer's Workflow
Avatar for Chris Coyier chriscoyier
695
190k
Docker and Python
Avatar for Tania Allard trallard
45
3.5k
Faster Mobile Websites
Avatar for Dean Hume deanohume
309
31k
How to Think Like a Performance Engineer
Avatar for Harry Roberts csswizardry
25
1.8k

Transcript

  1. How Do Large Language Models Acquire Factual Knowledge During Pretraining?

    ࡫໺ݚڀࣨɹD1 ໼໺ઍߛ Hoyeon Chang, Jinho Park, Seonghyeon Ye, Sohee Yang, Youngkyung Seo, Du-Seong Chang, Minjoon Seo NeurIPS 2025