In a three-stage end-to-end spoken language model, experience replay (mixing old data into later training) was the most effective mitigation against catastrophic forgetting, greatly outperforming model merging and LoRA scaling discounting.
The results demonstrate that expe- rience replay is the most effective method, with further perfor- mance gains achievable by combining it with other techniques
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models
In a three-stage end-to-end spoken language model, experience replay (mixing old data into later training) was the most effective mitigation against catastrophic forgetting, greatly outperforming model merging and LoRA scaling discounting.