Prompts with higher semantic density per token improve LLM accuracy by an average of 8.4 percentage points across five models and seven benchmarks, with no added tokens or latency.
Title resolution pending
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
-
Semantic Density Effect (SDE): Maximizing Information Per Token Improves LLM Accuracy
Prompts with higher semantic density per token improve LLM accuracy by an average of 8.4 percentage points across five models and seven benchmarks, with no added tokens or latency.