51
Beyond Semantics: Unreasonable Effectiveness of Reasonless Intermediate Tokens (arxiv.org)
10 hours ago | nyrikki | arxiv.org | frontpage
3
Do Think Tags Help LLMs Plan? (openreview.net)
a week ago | nyrikki | openreview.net | newest
3
(How) Do reasoning models reason? (arxiv.org)
a month ago | nyrikki | arxiv.org | newest
1
Equivalence of the Frame and Halting Problems (2020) [pdf] (philpapers.org)
5 months ago | nyrikki | philpapers.org | newest
2
GAO Agile Assessment Guide (2023) (gao.gov)
12 months ago | nyrikki | gao.gov | newest
2
Why Are Sensitive Functions Hard for Transformers? (arxiv.org)
a year ago | nyrikki | arxiv.org | newest
223
LLMs can't self-correct in reasoning tasks, DeepMind study finds (bdtechtalks.com)
a year ago | nyrikki | bdtechtalks.com | best