LLM reasoning / chain-of-thought
LiDER
Superseded baseline#54 of 772 most-superseded
Superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 1 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites LiDER as a baseline.
LiDER only considers model Lipschitz constants which can be implicitly related to the landscape of model outputs in a local region but does not consider the input data
Beaten on benchmarks
Head-to-head results where a newer method reports beating LiDER. Values are copied from the source paper's tables — verify against the cited paper.
STAR+ER-ACE beats LiDER
30.38 vs 27.94
accuracy · [ER-ACE + buffer size 200]
STAR: Stability-Inducing Weight Perturbation for Continual LearningSTAR+DER++ beats LiDER
61.76 vs 58.43
accuracy · [DER++ + buffer size 100]
STAR: Stability-Inducing Weight Perturbation for Continual Learning