Cover Image

Semantic Compression of LLM Instructions via Symbolic Metalanguages

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	van Gassen, Ernst
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Speaking of Language: Reflections on Metalanguage Research in NLP
by: Schneider, Nathan, et al.
Published: (2026)

Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting
by: Arbuzov, Mikhail L., et al.
Published: (2026)

Prism: A Minimal Compositional Metalanguage for Specifying Agent Behavior
by: Binard, Franck, et al.
Published: (2025)

NIM: Neuro-symbolic Ideographic Metalanguage for Inclusive Communication
by: Sharma, Prawaal, et al.
Published: (2025)

The Relative Monadic Metalanguage
by: Liell-Cock, Jack, et al.
Published: (2025)

LLMs that Understand Processes: Instruction-tuning for Semantics-Aware Process Mining
by: Pyrih, Vira, et al.
Published: (2025)

Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding
by: Figueiredo, Vanessa
Published: (2025)

Instruction Set and Language for Symbolic Regression
by: Lopez-Rubio, Ezequiel, et al.
Published: (2026)

Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
by: Xu, Lei, et al.
Published: (2025)

Multilingual Generative Retrieval via Cross-lingual Semantic Compression
by: Huang, Yuxin, et al.
Published: (2025)

Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression
by: Hou, Haowen, et al.
Published: (2024)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
by: Liu, Xiang, et al.
Published: (2025)

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
by: Liu, Xin, et al.
Published: (2025)

Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
by: Li, Zenan, et al.
Published: (2024)

Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs
by: Chen, Yi-Chun
Published: (2025)

Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
by: Deng, Jingcheng, et al.
Published: (2025)

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
by: Tang, Jiwei, et al.
Published: (2025)

Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations
by: Zhang, Xiao, et al.
Published: (2024)

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
by: Wang, Yiming, et al.
Published: (2023)

Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
by: Zhao, Zhenyu, et al.
Published: (2026)

SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
by: Wu, Shunlong, et al.
Published: (2026)

LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
by: Kulkarni, Atharv, et al.
Published: (2025)

98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router
by: Liu, Xunzhuo, et al.
Published: (2026)

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
by: Xu, Fangzhi, et al.
Published: (2023)

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
by: Song, Jiwon, et al.
Published: (2025)

Analyzing LLM Instruction Optimization for Tabular Fact Verification
by: Du, Xiaotang, et al.
Published: (2026)

Effectively Compress KV Heads for LLM
by: Yu, Hao, et al.
Published: (2024)

When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following
by: Harada, Keno, et al.
Published: (2025)

ProCut: LLM Prompt Compression via Attribution Estimation
by: Xu, Zhentao, et al.
Published: (2025)

DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM Inference
by: Ye, Jiancai, et al.
Published: (2026)

PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
by: Quan, Xin, et al.
Published: (2025)

Information Extraction from Conversation Transcripts: Neuro-Symbolic vs. LLM
by: Kwak, Alice Saebom, et al.
Published: (2025)

Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning
by: Verma, Pulkit, et al.
Published: (2025)

CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
by: Liu, Yilun, et al.
Published: (2023)

Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
by: Bronzini, Marco, et al.
Published: (2025)

Just CHOP: Embarrassingly Simple LLM Compression
by: Jha, Ananya Harsh, et al.
Published: (2023)

Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views
by: Fang, Feihao, et al.
Published: (2026)

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles
by: Pu, Xiao, et al.
Published: (2024)

SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation
by: Jiang, Hanqi, et al.
Published: (2026)

AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning
by: Dao, Alan, et al.
Published: (2025)