Empirical analysis of ASR error propagation in Korean spoken QA cascades shows consistent relative downstream degradation across LLMs and highlights single-character transcription errors as a language-specific failure mode.
Efficient memory management for large language model serving with PagedAttention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades
Empirical analysis of ASR error propagation in Korean spoken QA cascades shows consistent relative downstream degradation across LLMs and highlights single-character transcription errors as a language-specific failure mode.