N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator

• URL: http://arxiv.org/abs/2511.14195v1
• Date: Tue, 18 Nov 2025 07:03:58 GMT
• Title: N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator
• Abstract summary: N-GLARE operates entirely on the model's latent representations, bypassing the need for full text generation.<n>It characterizes hidden layer dynamics by analyzing the APT (Angular-Probabilistic Trajectory) of latent representations.<n>N-GLARE reproduces the discriminative trends of large-scale red-teaming tests at less than 1% of the token cost and the runtime cost.
• Score: 2.741826749835854
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating the safety robustness of LLMs is critical for their deployment. However, mainstream Red Teaming methods rely on online generation and black-box output analysis. These approaches are not only costly but also suffer from feedback latency, making them unsuitable for agile diagnostics after training a new model. To address this, we propose N-GLARE (A Non-Generative, Latent Representation-Efficient LLM Safety Evaluator). N-GLARE operates entirely on the model's latent representations, bypassing the need for full text generation. It characterizes hidden layer dynamics by analyzing the APT (Angular-Probabilistic Trajectory) of latent representations and introducing the JSS (Jensen-Shannon Separability) metric. Experiments on over 40 models and 20 red teaming strategies demonstrate that the JSS metric exhibits high consistency with the safety rankings derived from Red Teaming. N-GLARE reproduces the discriminative trends of large-scale red-teaming tests at less than 1\% of the token cost and the runtime cost, providing an efficient output-free evaluation proxy for real-time diagnostics.

Related papers

• Beyond the Syntax: Do Security Experts Trust LLMs for NIDS Rule Engineering? [70.17374586573033]
  This paper presents a human-centered investigation into Large Language Models (LLMs)-based NIDS rule engineering.<n>Our evaluation reveals a syntax-semantics paradox: although LLMs generate syntactically correct rules, experts find them only partially deployable.<n>While large-scale models consistently produce syntactically valid rules, small models are largely ineffective for IDS rule generation.
  arXiv  Detail & Related papers  (2026-07-07T07:09:56Z)
• Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks? [9.709556420480508]
  Large Language Models (LLMs) have advanced Graph Neural Networks (GNNs) by enriching node representations with semantic features.<n>We propose a robustness assessment framework that systematically evaluates LLM-enhanced GNNs under poisoning attacks.
  arXiv  Detail & Related papers  (2026-03-27T06:28:25Z)
• RACA: Representation-Aware Coverage Criteria for LLM Safety Testing [13.729870450773797]
  This paper introduces RACA, a novel set of coverage criteria specifically designed for AI safety testing.<n>We conduct comprehensive experiments to validate RACA's effectiveness, applicability, and generalization.<n>We also showcase its practical application in real-world scenarios, such as test set prioritization and attack prompt sampling.
  arXiv  Detail & Related papers  (2026-02-02T16:20:51Z)
• CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning [57.24524263804788]
  Code verifiers play a critical role in post-verification for LLM-based code generation.<n>Existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency.<n>We show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples.
  arXiv  Detail & Related papers  (2026-01-30T10:33:29Z)
• ParaVul: A Parallel Large Language Model and Retrieval-Augmented Framework for Smart Contract Vulnerability Detection [43.41293570032631]
  ParaVul is a retrieval-augmented framework to improve the reliability and accuracy of smart contract vulnerability detection.<n>We develop Sparse Low-Rank Adaptation (SLoRA) for LLM fine-tuning.<n>We construct a vulnerability contract dataset and develop a hybrid Retrieval-Augmented Generation (RAG) system.
  arXiv  Detail & Related papers  (2025-10-20T03:23:41Z)
• RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts [39.58550043591753]
  External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs.<n>We investigated how robust LLM-based guardrails are against additional information embedded in the context.
  arXiv  Detail & Related papers  (2025-10-06T19:20:43Z)
• ZeroFalse: Improving Precision in Static Analysis with LLMs [0.1759008116536278]
  Static Application Security Testing (SAST) tools are integral to modern software development, yet their adoption is undermined by excessive false positives.<n>We present ZeroFalse, a framework that integrates static analysis with large language models (LLMs) to reduce false positives while preserving coverage.
  arXiv  Detail & Related papers  (2025-10-02T20:07:25Z)
• GLASS: Test-Time Acceleration for LLMs via Global-Local Neural Importance Aggregation [12.921040231832082]
  We introduce A/I-GLASS: Activation- and Impact-based Global-Local neural importance aggregation for feed-forward network SparSification.<n> Empirical results across multiple Large Language Models (LLMs) and benchmarks demonstrate that GLASS significantly outperforms prior training-free methods.
  arXiv  Detail & Related papers  (2025-08-19T22:50:20Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders [50.52694757593443]
  Existing SAE training algorithms often lack rigorous mathematical guarantees and suffer from practical limitations.<n>We first propose a novel statistical framework for the feature recovery problem, which includes a new notion of feature identifiability.<n>We introduce a new SAE training algorithm based on bias adaptation'', a technique that adaptively adjusts neural network bias parameters to ensure appropriate activation sparsity.
  arXiv  Detail & Related papers  (2025-06-16T20:58:05Z)
• ReGA: Representation-Guided Abstraction for Model-based Safeguarding of LLMs [0.9285458070502282]
  Large Language Models (LLMs) have achieved significant success in various tasks, yet concerns about their safety and security have emerged.<n>To analyze and monitor machine learning models, model-based analysis has demonstrated notable potential in stateful deep neural networks.<n>We propose ReGA, a model-based analysis framework with representation-guided abstraction, to safeguard LLMs against harmful prompts and generations.
  arXiv  Detail & Related papers  (2025-06-02T15:17:38Z)
• Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space [92.6187727249868]
  We introduce LatentSeek, a framework that enhances reasoning through Test-Time Instance-level Adaptation (TTIA) within the model's latent space.<n>LatentSeek is evaluated on a range of reasoning benchmarks, including GSM8K, MATH-500, and AIME2024.<n>Results show that LatentSeek consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-05-19T16:26:02Z)
• LLM-Safety Evaluations Lack Robustness [58.334290876531036]
  We argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise.<n>We propose a set of guidelines for reducing noise and bias in evaluations of future attack and defense papers.
  arXiv  Detail & Related papers  (2025-03-04T12:55:07Z)
• Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions [60.31496362993982]
  Large language models (LLMs) frequently generate confident yet inaccurate responses.<n>We present a novel, test-time approach to detecting model hallucination through systematic analysis of information flow.
  arXiv  Detail & Related papers  (2024-12-13T16:14:49Z)

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.