$Cover Image$

The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Johnson, Warren
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Compression Method Matters: Benchmark-Dependent Output Dynamics in LLM Prompt Compression
by: Johnson, Warren
Published: (2026)

From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression
by: Choi, Eunseong, et al.
Published: (2024)

Large Language Models Can Better Understand Knowledge Graphs Than We Thought
by: Dai, Xinbang, et al.
Published: (2024)

CodeNER: Code Prompting for Named Entity Recognition
by: Han, Sungwoo, et al.
Published: (2025)

Tokenization Is More Than Compression
by: Schmidt, Craig W., et al.
Published: (2024)

More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
by: Liu, Ming
Published: (2026)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
by: Saji, Alan, et al.
Published: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
by: Peters, Sydney, et al.
Published: (2025)

Prompt Compression in Production Task Orchestration: A Pre-Registered Randomized Trial
by: Johnson, Warren, et al.
Published: (2026)

Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt Optimization
by: Elganayni, Mohamed Hesham, et al.
Published: (2026)

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
by: Orgad, Hadas, et al.
Published: (2024)

EasyMath: A 0-shot Math Benchmark for SLMs
by: Karki, Drishya, et al.
Published: (2025)

Lossless Prompt Compression via Dictionary-Encoding and In-Context Learning: Enabling Cost-Effective LLM Analysis of Repetitive Data
by: de Campos, Andresa Rodrigues, et al.
Published: (2026)

Streamlining Redundant Layers to Compress Large Language Models
by: Chen, Xiaodong, et al.
Published: (2024)

Prompt-Time Symbolic Knowledge Capture with Large Language Models
by: Çöplü, Tolga, et al.
Published: (2024)

Large Language Model (LLM) Bias Index -- LLMBI
by: Oketunji, Abiodun Finbarrs, et al.
Published: (2023)

CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge
by: Chen, Zhangquan, et al.
Published: (2024)

Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging
by: Cacioli, Jon-Paul
Published: (2026)

Prompt-Time Ontology-Driven Symbolic Knowledge Capture with Large Language Models
by: Çöplü, Tolga, et al.
Published: (2024)

APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification
by: Chernodub, Artem, et al.
Published: (2025)

Many LLMs Are More Utilitarian Than One
by: Keshmirian, Anita, et al.
Published: (2025)

InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models
by: Juseon-Do, et al.
Published: (2024)

Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression
by: Baxi, Rahul
Published: (2025)

Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt Structure
by: Devbunova, Viliana
Published: (2026)

Enhancing Sentiment Classification and Irony Detection in Large Language Models through Advanced Prompt Engineering Techniques
by: Schmitt, Marvin, et al.
Published: (2026)

NeuralNexus at BEA 2025 Shared Task: Retrieval-Augmented Prompting for Mistake Identification in AI Tutors
by: Naeem, Numaan, et al.
Published: (2025)

Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language
by: Kinas, Remigiusz, et al.
Published: (2026)

Truth as a Compression Artifact in Language Model Training
by: Krestnikov, Konstantin
Published: (2026)

Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance
by: Cacioli, Jon-Paul
Published: (2026)

Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles
by: Budagam, Devichand, et al.
Published: (2024)

Is Our Chatbot Telling Lies? Assessing Correctness of an LLM-based Dutch Support Chatbot
by: Lassche, Herman, et al.
Published: (2024)

Analyzing LLM Reasoning to Uncover Mental Health Stigma
by: Sankar, Sreehari, et al.
Published: (2026)

Xinyu: An Efficient LLM-based System for Commentary Generation
by: Wu, Yiquan, et al.
Published: (2024)

Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation
by: Cacioli, Jon-Paul
Published: (2026)

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
by: Siegel, Noah Y., et al.
Published: (2025)

Presumed Cultural Identity: How Names Shape LLM Responses
by: Pawar, Siddhesh, et al.
Published: (2025)

Weber's Law in Transformer Magnitude Representations: Efficient Coding, Representational Geometry, and Psychophysical Laws in Language Models
by: Cacioli, Jon-Paul
Published: (2026)

On the Effectiveness of LLM-Specific Fine-Tuning for Detecting AI-Generated Text
by: Gromadzki, Michał, et al.
Published: (2026)

Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation
by: Cacioli, Jon-Paul
Published: (2026)

Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
by: Baltaji, Razan, et al.
Published: (2024)