A hybrid local-plus-cloud LLM pipeline cuts input tokens by about 6x and improves F1 on Schwartz value identification benchmarks compared with direct LLM prompting.
Qlora: Efficient fine- tuning of quantized llms,
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
-
EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs
A hybrid local-plus-cloud LLM pipeline cuts input tokens by about 6x and improves F1 on Schwartz value identification benchmarks compared with direct LLM prompting.