PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails

• URL: http://arxiv.org/abs/2608.15673v1
• Date: Sun, 16 Aug 2026 10:58:19 GMT
• Title: PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails
• Abstract summary: Policy prompting and LLM-as-a-judge pipelines often overlap the tasks of semantic grounding and policy reasoning.<n>To separate grounding and reasoning roles, we propose PL-Guard, a neurosymbolic guardrail architecture.<n>On the XSTest benchmark, an offline Qwen-based evaluator finds that PL-Guard with a hand-curated policy reduces unsafe compliance from 22.0% for the base model to 0.5%.
• Score: 5.448131579126687
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model guardrails can be viewed as policy-consistency problems: a system must determine which policy-relevant facts hold in a prompt-response pair and what those facts imply under a given policy. Common approaches, including policy prompting and LLM-as-a-judge pipelines, often overlap the tasks of semantic grounding and policy reasoning: the model both interprets the prompt-response pair and reasons about whether a policy has been violated. This can lead to unsafe compliance with harmful prompts, or refusals to assist benign ones. To separate grounding and reasoning roles, we propose PL-Guard, a neurosymbolic guardrail architecture. Using a symbolic policy interface consisting of predicates and ProbLog rules, a local LLM grounds prompt-response pairs into predicate probabilities using renormalized True/False token scores, while ProbLog performs explicit probabilistic rule inference over the symbolic policy. On the XSTest benchmark, an offline Qwen-based evaluator finds that PL-Guard with a hand-curated policy reduces unsafe compliance from 22.0% for the base model to 0.5%, and below the 6.0% rate of an LLM-as-a-judge baseline. This comes at the cost of higher over-refusal than the LLM-as-a-judge baseline, 14.4% versus 5.2%. These results suggest that separating neural grounding from probabilistic symbolic reasoning can expose the safety-helpfulness tradeoff while making the guardrail's intermediate reasoning steps explicit and auditable.

Related papers

• LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL [64.4276583943816]
  Reinforcement learning for non-verifiable instruction relies on judges with prompt-specific rubrics as reward signals.<n>While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static.<n>This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal.
  arXiv  Detail & Related papers  (2026-07-05T17:05:13Z)
• SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing [25.10453609307193]
  In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies.<n>In this work, we study this setting under the paradigm of in-context policy guardrailing, where guardrails predict safety violations based on policy specifications provided in context.<n>We introduce SafePyramid, a safety benchmark comprising 1,000 multi-turn conversations across 10 domains and 3,000 corresponding application-specific policies, which together contain 61,699 distinct natural-language rules.
  arXiv  Detail & Related papers  (2026-06-29T07:27:22Z)
• LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails [41.04710068888387]
  We introduce Latent Policy Guardrail (LPG), a guardrail framework that learnssemantic latent deliberation over dynamic policies.<n>Across policy guardrail benchmarks, LPG-4B reaches 84.5% average safety accuracy and 77.9% F1 by compressing deliberation into just 10 latent tokens.
  arXiv  Detail & Related papers  (2026-05-17T08:35:38Z)
• LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applications [51.56484100374058]
  We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow.<n>The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract.<n>We evaluate the harness on ticket-routing and BEIR tasks with full Azure matrix coverage.
  arXiv  Detail & Related papers  (2026-03-28T18:03:32Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• Bayesian Evaluation of Large Language Model Behavior [11.847752638476257]
  It is increasingly important to evaluate how text generation systems based on large language models behave.<n>Existing approaches to evaluation often neglect statistical uncertainty quantification.<n>We present two case studies applying a Bayesian approach for quantifying uncertainty in binary evaluation metrics.
  arXiv  Detail & Related papers  (2025-11-04T19:51:46Z)
• Policy-Aware Generative AI for Safe, Auditable Data Access Governance [0.0]
  We present a policy aware controller that uses a large language model (LLM) to interpret natural language requests against written policies and metadata, not raw data.<n>The system, implemented with Google Gemini2.0 Flash, executes a six-stage reasoning framework with early hard policy gates and deny by default.
  arXiv  Detail & Related papers  (2025-10-27T16:10:55Z)
• Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference [16.706959860667133]
  It remains unclear whether large language models (LLMs) can handle rigorous and trustworthy statistical causal inference.<n>The CausalPitfalls benchmark provides essential guidance and quantitative metrics to advance the development of trustworthy causal reasoning systems.
  arXiv  Detail & Related papers  (2025-05-19T23:06:00Z)
• 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)
• OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models [68.17018458283651]
  This work focuses on the offline evaluation of the chain-of-thought capabilities of LLMs. We use knowledge graphs (e.g., Wikidata5m) to provide feedback on the generated chain of thoughts. We show how to optimize LLMs based on the proposed evaluation method.
  arXiv  Detail & Related papers  (2024-10-31T07:48:44Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)

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.