Sequential post-training of LLMs induces representation collapse that correlates with reduced plasticity, weaker generalization, and poorer calibration, with lightweight interventions tested to mitigate it.
Enhancing pretrained model-based continual representation learning via guided random projection.arXiv preprint arXiv:2603.19145, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Representation Collapse in Sequential Post-Training of Large Language Models
Sequential post-training of LLMs induces representation collapse that correlates with reduced plasticity, weaker generalization, and poorer calibration, with lightweight interventions tested to mitigate it.