Method Drift›LLM reasoning / chain-of-thought
OCM
LLM reasoning / chain-of-thought
superseded — cited as a baseline and beaten by newer methods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 OCM as a baseline.
“In contrast to STAR, OCM and DualHSIC do not consider the change in model outputs in the local parameter neighbourhood”
— STAR: Stability-Inducing Weight Perturbation for Continual Learning
Beaten on benchmarks
Head-to-head results where a newer method reports beating OCM. Values are copied from the source paper's tables — verify against the cited paper.
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+ER-ACE beats OCM · accuracy [ER-ACE + buffer size 100]
60.69 vs 57.18
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+ER-ACE beats OCM · accuracy [ER-ACE + buffer size 200]
67.58 vs 64.65
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+ER-ACE beats OCM · accuracy [ER-ACE + buffer size 500]
75.44 vs 70.86
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+ER-ACE beats OCM · accuracy [ER-ACE + buffer size 2000]
51.67 vs 49.03
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+ER-ACE beats OCM · accuracy [ER-ACE + buffer size 1000]
21.06 vs 20.32
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+ER-ACE beats OCM · accuracy [ER-ACE + buffer size 5000]
31.01 vs 28.57
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+DER++ beats OCM · accuracy [DER++ + buffer size 100]
61.76 vs 59.25
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+DER++ beats OCM · accuracy [DER++ + buffer size 200]
68.60 vs 65.81
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+DER++ beats OCM · accuracy [DER++ + buffer size 500]
76.52 vs 73.53
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+DER++ beats OCM · accuracy [DER++ + buffer size 2000]
53.24 vs 52.25
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+DER++ beats OCM · accuracy [DER++ + buffer size 1000]
22.4 vs 20.93
- STAR: Stability-Inducing Weight Perturbation for Continual Learning
STAR+DER++ beats OCM · accuracy [DER++ + buffer size 5000]
33.36 vs 31.16