Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL

• URL: http://arxiv.org/abs/2603.18174v1
• Date: Wed, 18 Mar 2026 18:14:34 GMT
• Title: Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL
• Abstract summary: A class of routing and access-control systems base their decisions on probabilistic ML signals.<n>Two such signals, declared over categories the author intended to be disjoint, can both clear their thresholds on the same query and silently route it to the wrong model.<n>We show that for the embedding case, which dominates in practice, replacing independent thresholding with a temperature-scaled softmax partitions the embedding space into Voronoi regions where co-firing is impossible.
• Score: 11.868735376461446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conflict detection in policy languages is a solved problem -- as long as every rule condition is a crisp Boolean predicate. BDDs, SMT solvers, and NetKAT all exploit that assumption. But a growing class of routing and access-control systems base their decisions on probabilistic ML signals: embedding similarities, domain classifiers, complexity estimators. Two such signals, declared over categories the author intended to be disjoint, can both clear their thresholds on the same query and silently route it to the wrong model. Nothing in the compiler warns about this. We characterize the problem as a three-level decidability hierarchy -- crisp conflicts are decidable via SAT, embedding conflicts reduce to spherical cap intersection, and classifier conflicts are undecidable without distributional knowledge -- and show that for the embedding case, which dominates in practice, replacing independent thresholding with a temperature-scaled softmax partitions the embedding space into Voronoi regions where co-firing is impossible. No model retraining is needed. We implement the detection and prevention mechanisms in the Semantic Router DSL, a production routing language for LLM inference, and discuss how the same ideas apply to semantic RBAC and API gateway policy.

Related papers

• SeGDeP: Semantic- and Geometric-Aware Decoupled Prompts for Reasoning Segmentation [51.46828526392219]
  Reasoning segmentation converts an implicit linguistic conclusion into a precise mask.<n>Existing MLLM-segmenter interfaces either use a special trigger or compress both signals into one context.<n>We present SeGDeP, an explicit what-where interface.
  arXiv  Detail & Related papers  (2026-09-08T15:11:32Z)
• On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models [0.0]
  We formalize prompted systems as Prompted Action Models with control-authoritative actions.<n>We prove Semantic-Faithful Control (SFC) is unachievable within the shared pipeline.<n>We identify the root cause and the class of solution it demands.
  arXiv  Detail & Related papers  (2026-06-25T21:52:29Z)
• Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation [53.844308305341166]
  We propose textbfAgentic ASR, a closed-loop framework that combines a single-pass ASR front-end with semantic correction, intent routing, and reasoning-based editing.<n> Experiments on multilingual, named-entity-intensive, and code-switching benchmarks show that iterative interaction consistently reduces semantic errors.
  arXiv  Detail & Related papers  (2026-05-28T06:23:31Z)
• Neural Router: Semantic Content Matching for Agentic AI [41.39228253084888]
  Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI.<n> Framed as offline multi-label retrieval over three public datasets, our central contribution is a two-crossover cost-accuracy characterisation.
  arXiv  Detail & Related papers  (2026-05-25T10:58:53Z)
• CAN-QA: A Question-Answering Benchmark for Reasoning over In-Vehicle CAN Traffic [12.047310162349584]
  We introduce CAN-QA, the first benchmark that reformulates CAN traffic analysis as a question-answering (QA) task.<n>Can-QA converts raw CAN logs into temporally segmented windows and applies deterministic rule-based templates to generate natural-language questions.<n>Our results indicate that, although these models capture superficial statistical regularities, they struggle with temporal reasoning, multi-condition inference, and higher-level behavioral interpretation.
  arXiv  Detail & Related papers  (2026-04-27T19:20:59Z)
• How LLMs Fail and Generalize in RTL Coding for Hardware Design? [56.361436215029045]
  We introduce a new error taxonomy grounded in problem solvability, inspired by cognitive theory.<n>Our taxonomy categorizes failures into syntactic, semantic, solvable functional, and unsolvable functional types.
  arXiv  Detail & Related papers  (2026-04-26T14:34:49Z)
• From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification [10.651054435747385]
  The Semantic Router DSL is a non-Turing-complete policy language deployed in production for per-request inference.<n>This paper extends the same language from stateless, per-request routing to multi-step agent routing.
  arXiv  Detail & Related papers  (2026-03-28T15:04:31Z)
• Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities [13.166560071380621]
  The Model Context Protocol (MCP) is a proposed interoperability standard that unifies how AI agents connect with external tools and data sources.<n>To be compatible with diverse AI agents, the MCP specification relaxes many behavioral constraints into optional clauses, leading to misuse-prone SDK implementation.<n>We present the first systematic framework for analyzing this new attack surface across multi-language MCP SDKs.
  arXiv  Detail & Related papers  (2026-03-10T18:57:48Z)
• An LLM-driven Scenario Generation Pipeline Using an Extended Scenic DSL for Autonomous Driving Safety Validation [4.602386383455713]
  Real-world crash reports are valuable for scenario-based testing of autonomous driving systems.<n>Current methods cannot effectively translate this multimodal data into precise, executable simulation scenarios.<n>We propose a scalable and verifiable pipeline that uses a large language model and a probabilistic intermediate representation.
  arXiv  Detail & Related papers  (2026-02-24T07:44:26Z)
• Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA [61.12136997430116]
  Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices with multi-task datasets to collaboratively fine-tune a large language model (LLM) by exchanging locally updated parameters with a subset of neighboring devices via wireless connections for knowledge integration.<n> directly aggregating parameters fine-tuned on heterogeneous datasets induces three primary issues across the DFL life-cycle: (i) catastrophic knowledge forgetting during fine-tuning process, arising from conflicting update directions caused by data heterogeneity; (ii) textitinefficient communication and convergence during model aggregation process,
  arXiv  Detail & Related papers  (2026-02-24T02:45:32Z)
• vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models [8.433829083279518]
  vLLM Semantic Router is a signal-driven decision routing framework for Mixture-of-Modality (MoM) model deployments.<n>The system extracts heterogeneous signal types from each request.<n>Different deployment scenarios are expressed as different signal-decision configurations over the same architecture.
  arXiv  Detail & Related papers  (2026-02-23T15:00:01Z)
• The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation [11.984098021215878]
  We introduce the Semantic-Preserving Adrial Code Injection (SPACI) Framework and the Abstract Syntax Tree-Aware Semantic Injection Protocol (AST-ASIP)<n>These methods exploit the Syntax-Semantics Gap by embedding adversarial directives into syntactically inert regions (trivia nodes) of the Abstract Syntax Tree.<n>Through a large-scale evaluation of 9 SOTA models across 25,000 submissions in Python, C, C++, and Java, we reveal catastrophic failure rates (>95%) in high-capacity open-weights models like DeepSeek-V3.
  arXiv  Detail & Related papers  (2026-01-29T07:40:58Z)
• STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model [71.35577462669856]
  We propose a robust, provably secure linguistic steganography with diffusion language models (DLMs)<n>We introduce error correction strategies, including pseudo-random error correction and neighborhood search correction, during steganographic extraction.
  arXiv  Detail & Related papers  (2026-01-21T08:58:12Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• G-CSEA: A Graph-Based Conflict Set Extraction Algorithm for Identifying Infeasibility in Pseudo-Boolean Models [0.5773629510985792]
  A common diagnostic approach is to compute Irreducible Infeasible Subsets (IIS)<n>We consider models formulated using pseudo-Boolean constraints with inequality relations over binary variables.<n>Our method constructs an implication graph during constraint propagation and, upon detecting a conflict, traces all contributing constraints across both decision branches.
  arXiv  Detail & Related papers  (2025-09-16T16:09:30Z)
• Few-shot Policy (de)composition in Conversational Question Answering [54.259440408606515]
  We propose a neuro-symbolic framework to detect policy compliance using large language models (LLMs) in a few-shot setting.<n>We show that our approach soundly reasons about policy compliance conversations by extracting sub-questions to be answered, assigning truth values from contextual information, and explicitly producing a set of logic statements from the given policies.<n>We apply this approach to the popular PCD and conversational machine reading benchmark, ShARC, and show competitive performance with no task-specific finetuning.
  arXiv  Detail & Related papers  (2025-01-20T08:40:15Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings [50.524054820564395]
  We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and zero-resource languages.
  arXiv  Detail & Related papers  (2020-12-03T19:24:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.