arXiv subjects

Wen G. Gong

Publications and source records attributed to Wen G. Gong.

6 recordsLinked to original sources

arXiv2026

SPL: Orchestrating Workflows with Declarative Deterministic-Probabilistic Composition

We present SPL (Structured Prompt Language), a declarative language that composes deterministic and probabilistic computation modes in a single specification. While existing frameworks separate these -- orchestration systems (AutoGen, CrewAI, LangGraph) for LLM calls, symbolic tools (SymPy, SageMath, Lean) for computation -- SPL unifies them. It provides GENERATE/EVALUATE for probabilistic computation and SOLVE/ASSERT for deterministic computation, sharing syntax, variable bindings, and runtime routing. A .spl specification runs unchanged across local nodes (Ollama), cloud APIs (OpenRouter, Anthropic), and distributed grids (Momagrid), with model and verifier selection deferred to invocation time. We validate SPL through an extensive 78-recipe cookbook and a controlled 1,200-run experiment (10 models x 20 problems x 2 arms x 3 repetitions; the 20 problems span 6 difficulty tiers). The solver arm achieves 82-93% machine-verified correctness (sonnet-4-6: 85%, gemma4:e2b: 93%) while the LLM-only arm measures output production without mathematical verification, making the comparison one of verified correctness against unverified fluency. A backend difficulty gradient emerges (SymPy 78%, Sage 54%), and the dominant failure mode is solver_error (kernel-rejected expressions), not format non-compliance.

cs.PL↗

arXiv2026

Structured Prompt Language: Declarative Context Management for LLMs

We present SPL (Structured Prompt Language), a declarative SQL-inspired language that treats large language models as generative knowledge bases and their context windows as constrained resources. SPL provides explicit WITH BUDGET/LIMIT token management, an automatic query optimizer, EXPLAIN transparency analogous to SQL's EXPLAIN ANALYZE, and native integration of retrieval-augmented generation (RAG) and persistent memory in a single declarative framework. SPL-flow extends SPL into resilient agentic pipelines with a three-tier provider fallback strategy (Ollama -> OpenRouter -> self-healing retry) fully transparent to the .spl script. Five extensions demonstrate the paradigm's breadth: (1) Text2SPL (multilingual NL->SPL translation); (2) Mixture-of-Models (MoM) routing that dispatches each PROMPT to a domain-specialist model at runtime; (3) Logical Chunking, an intelligent strategy for documents exceeding a single context window--expressed naturally through SPL's existing CTE syntax with no new constructs, decomposing a large query into a Map-Reduce pipeline that reduces attention cost from O(N^2) to O(N^2/k) and runs identically on cloud (parallel) or local hardware (sequential); (4) SPL-flow, a declarative agentic orchestration layer with resilient three-tier provider fallback; and (5) BENCHMARK for parallel multi-model comparison with automatic winner persistence. We provide a formal EBNF grammar, two pip-installable Python packages (spl-llm, spl-flow), and comparison against Prompty, DSPy, and LMQL. SPL reduces prompt boilerplate by 65% on average, surfaces a 68x cost spread across model tiers as a pre-execution signal, and runs the identical .spl script at $0.002 on OpenRouter or at zero marginal cost on a local Ollama instance--without modification.

cs.CL↗

arXiv2026

Reranker Optimization via Geodesic Distances on k-NN Manifolds

Current neural reranking approaches for retrieval-augmented generation (RAG) rely on cross-encoders or large language models (LLMs), requiring substantial computational resources and exhibiting latencies of 3-5 seconds per query. We propose Maniscope, a geometric reranking method that computes geodesic distances on k-nearest neighbor (k-NN) manifolds constructed over retrieved document candidates. This approach combines global cosine similarity with local manifold geometry to capture semantic structure that flat Euclidean metrics miss. Evaluating on eight BEIR benchmark datasets (1,233 queries), Maniscope outperforms HNSW graph-based baseline on the three hardest datasets (NFCorpus: +7.0%, TREC-COVID: +1.6%, AorB: +2.8% NDCG@3) while being 3.2x faster (4.7 ms vs 14.8 ms average). Compared to cross-encoder rerankers, Maniscope achieves within 2% accuracy at 10-45x lower latency. On TREC-COVID, LLM-Reranker provides only +0.5% NDCG@3 improvement over Maniscope at 840x higher latency, positioning Maniscope as a practical alternative for real-time RAG deployment. The method requires O(N D + M^2 D + M k log k) complexity where M << N , enabling sub-10 ms latency. We plan to release Maniscope as open-source software.

cs.CL↗

arXiv2025

Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB) may mask fundamental alignment shortcomings. We introduce Semantic Affinity (SA), a bounded (between 0 and 1) metric measuring inter-lingual to intra-lingual spread ratio using cosine distance, combined with PHATE visualization in our Semanscope framework. Benchmarking 13 models across 4 datasets (52 experiments) reveals a three-tier structure: (1) Top BERT models (LaBSE SA = 0.70, USE SA = 0.68, S-BERT SA = 0.68) achieve strong alignment via translation-pair supervision; (2) LLM embeddings plateau at SA between 0.55 and 0.61 regardless of 0.6 B to 8 B scale; (3) MLM-only BERT models (mBERT, XLM-R, SA < 0.50) fail despite more than 100 language training. Training objective, not architecture or scale, determines alignment. Oracle Bone primitives (1200 BCE) expose semantic drift-models learn corpus patterns rather than cognitive primitives. This work provides semantic benchmarking to help practitioners select quality multilingual embeddings from hundreds of available models, showing cross-lingual alignment requires explicit translation supervision, not merely model scale or multilingual data.

cs.CL↗

arXiv2025

Geometric Structures and Patterns of Meaning: A PHATE Manifold Analysis of Chinese Character Embeddings

We systematically investigate geometric patterns in Chinese character embeddings using PHATE manifold analysis. Through cross-validation across seven embedding models and eight dimensionality reduction methods, we observe clustering patterns for content words and branching patterns for function words. Analysis of over 1000 Chinese characters across 12 semantic domains reveals that geometric complexity correlates with semantic content: meaningful characters exhibit rich geometric diversity while structural radicals collapse into tight clusters. The comprehensive child-network analysis (123 phrases) demonstrates systematic semantic expansion from elemental character. These findings provide computational evidence supporting traditional linguistic theory and establish a novel framework for geometric analysis of semantic organization.

cs.CL↗

arXiv2025

A New Exploration into Chinese Characters: from Simplification to Deeper Understanding

This paper presents a novel approach to Chinese characters through the lens of physics, network analysis, and natural systems. Computational analysis of over 6,000 characters identified 422 elemental characters as fundamental building blocks. Using a physics-inspired "Zi-Matrix" model, we analyzed character structure across eleven spatial positions, revealing systematic patterns in component relationships and semantic extension. Our research demonstrates that Chinese characters exhibit properties of natural systems: emergent complexity, self-organization, and adaptive resilience. The Fibonacci sequence provides an organizing framework for understanding character evolution, from simple pictographs to sophisticated abstractions. Case studies of character families and semantic networks show how meaning radiates from concrete to abstract domains while maintaining coherent principles. By viewing Chinese characters as a living system, this research transcends mere simplification to reveal how human cognition organizes and transmits knowledge. While the elemental character set reduces memorization burden, it also illuminates profound connections between language, thought, and natural patterns. Chinese characters emerge not just as tools for communication, but as windows into human understanding. This perspective, combined with AI-assisted learning approaches, promises to transform language education from knowledge mastery to meaning discovery, bridging traditional wisdom with modern computational methods.

physics.soc-ph↗