Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Semantic Density Effect (SDE): Maximizing Information Per Token Improves LLM Accuracy

About

We introduce the Semantic Density Effect (SDE): the empirical finding that prompts carrying higher semantic information per token consistently produce more accurate, focused, and less hallucinated outputs across all major LLM families. SDE is defined as the ratio of semantically loaded tokens to total prompt tokens, adjusted for redundancy and concreteness. Unlike prior prompt optimization techniques that add tokens (Chain of Thought), duplicate the prompt (Prompt Repetition), or reorder components (Instruction Placement Effect), SDE improves performance by removing or replacing low-information tokens while preserving or sharpening the semantic signal. Evaluated across five frontier models and seven benchmarks, ultra-dense prompts (SDE > 0.80) outperform diluted counterparts by an average of +8.4 percentage points with 0 additional tokens and 0 latency overhead. Combined with Instruction Placement Effect (IPE), the gain reaches +11.7 percentage points

Amr Ahmed• 2026

Related benchmarks

TaskDatasetResultRank
Question AnsweringOpenBookQA
Accuracy Improvement Delta6
14
Information RetrievalNameIndex
Accuracy Improvement (Δ)16.1
5
Information RetrievalMiddleMatch
Accuracy Improvement (Δ)13.3
5
Mathematical ReasoningGSM8K
Accuracy Improvement (GSM8K)5.7
5
Mathematical ReasoningMATH
Accuracy Improvement Delta10.2
5
Meta-evaluationOverall (Average)
Accuracy Improvement9.7
5
Multi-task Knowledge EvaluationMMLU-Pro
Accuracy Improvement9.1
5
Question AnsweringARC Challenge
Accuracy Improvement (Δ)7.4
5
Showing 8 of 8 rows

Other info

Follow for update