Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Ahmed, Amr
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy
par: Shi, Xiaofeng, et autres
Publié: (2025)

LLM as a Broken Telephone: Iterative Generation Distorts Information
par: Mohamed, Amr, et autres
Publié: (2025)

SP^2DPO: An LLM-assisted Semantic Per-Pair DPO Generalization
par: He, Chaoyue, et autres
Publié: (2026)

MoLoRA: Composable Specialization via Per-Token Adapter Routing
par: Shah, Shrey, et autres
Publié: (2026)

Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining
par: Feng, Steven, et autres
Publié: (2024)

Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
par: Nam, Hyunji, et autres
Publié: (2026)

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
par: Chen, Yicheng, et autres
Publié: (2025)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
par: Qian, Chen, et autres
Publié: (2025)

Broken-Token: Filtering Obfuscated Prompts by Counting Characters-Per-Token
par: Zychlinski, Shaked, et autres
Publié: (2025)

Semantic Tokens in Retrieval Augmented Generation
par: Suro, Joel
Publié: (2024)

Revisiting the Uniform Information Density Hypothesis in LLM Reasoning
par: Gwak, Minju, et autres
Publié: (2025)

SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling
par: Liu, Dong, et autres
Publié: (2025)

CATP: Cross-Attention Token Pruning for Accuracy Preserved Multimodal Model Inference
par: Liao, Ruqi, et autres
Publié: (2024)

The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods
par: Badhe, Sanket, et autres
Publié: (2026)

Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection
par: Chowdhury, Anjir Ahmed, et autres
Publié: (2026)

When Safety Blocks Sense: Measuring Semantic Confusion in LLM Refusals
par: Anonto, Riad Ahmed, et autres
Publié: (2025)

PersLLM: A Personified Training Approach for Large Language Models
par: Zeng, Zheni, et autres
Publié: (2024)

Extending Token Computation for LLM Reasoning
par: Liao, Bingli, et autres
Publié: (2024)

Discovering Multi-Scale Semantic Structure in Text Corpora Using Density-Based Trees and LLM Embeddings
par: Haschka, Thomas, et autres
Publié: (2025)

One Token Is Enough: Improving Diffusion Language Models with a Sink Token
par: Zhang, Zihou, et autres
Publié: (2026)

TimeStampEval: A Simple LLM Eval and a Little Fuzzy Matching Trick to Improve Search Accuracy
par: McCammon, James
Publié: (2025)

InFact: Informativeness Alignment for Improved LLM Factuality
par: Cohen, Roi, et autres
Publié: (2025)

AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy
par: Schoenegger, Philipp, et autres
Publié: (2024)

KV Prediction for Improved Time to First Token
par: Horton, Maxwell, et autres
Publié: (2024)

LLM-Oriented Token-Adaptive Knowledge Distillation
par: Xie, Xurong, et autres
Publié: (2025)

HeartLLM: Discretized ECG Tokenization for LLM-Based Diagnostic Reasoning
par: Yang, Jinning, et autres
Publié: (2025)

Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context
par: Trinh, Viet Anh, et autres
Publié: (2025)

Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
par: Wei, Lei, et autres
Publié: (2026)

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
par: Dai, Lu, et autres
Publié: (2025)

Token Masking Improves Transformer-Based Text Classification
par: Xu, Xianglong, et autres
Publié: (2025)

SD-E$^2$: Semantic Exploration for Reasoning Under Token Budgets
par: Mishra, Kshitij, et autres
Publié: (2026)

Explainability-Based Token Replacement on LLM-Generated Text
par: Mohammadi, Hadi, et autres
Publié: (2025)

Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization
par: Chen, Yile, et autres
Publié: (2025)

GPS: General Per-Sample Prompter
par: Batorski, Pawel, et autres
Publié: (2025)

AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
par: Qing, Liu, et autres
Publié: (2026)

Learning to Maximize Mutual Information for Chain-of-Thought Distillation
par: Chen, Xin, et autres
Publié: (2024)

Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models
par: Huang, Liangjie, et autres
Publié: (2025)

Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning
par: Kim, Minwu, et autres
Publié: (2025)

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
par: Sawarkar, Kunal, et autres
Publié: (2024)

Tokenization Matters: Improving Zero-Shot NER for Indic Languages
par: Pattnayak, Priyaranjan, et autres
Publié: (2025)