Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

• URL: http://arxiv.org/abs/2506.13901v1
• Date: Mon, 16 Jun 2025 18:22:28 GMT
• Title: Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations
• Abstract summary: We introduce the Alignment Quality Index (AQI) to assess large language models' alignment.<n>AQI captures clustering quality to detect hidden misalignments and jailbreak risks, even when outputs appear compliant.<n>We also propose the LITMUS dataset to facilitate robust evaluation under challenging conditions.
• Score: 8.454242629883488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Alignment is no longer a luxury, it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must reliably reflect human-aligned values and safety constraints. Yet current evaluations rely heavily on behavioral proxies such as refusal rates, G-Eval scores, and toxicity classifiers, all of which have critical blind spots. Aligned models are often vulnerable to jailbreaking, stochasticity of generation, and alignment faking. To address this issue, we introduce the Alignment Quality Index (AQI). This novel geometric and prompt-invariant metric empirically assesses LLM alignment by analyzing the separation of safe and unsafe activations in latent space. By combining measures such as the Davies-Bouldin Score (DBS), Dunn Index (DI), Xie-Beni Index (XBI), and Calinski-Harabasz Index (CHI) across various formulations, AQI captures clustering quality to detect hidden misalignments and jailbreak risks, even when outputs appear compliant. AQI also serves as an early warning signal for alignment faking, offering a robust, decoding invariant tool for behavior agnostic safety auditing. Additionally, we propose the LITMUS dataset to facilitate robust evaluation under these challenging conditions. Empirical tests on LITMUS across different models trained under DPO, GRPO, and RLHF conditions demonstrate AQI's correlation with external judges and ability to reveal vulnerabilities missed by refusal metrics. We make our implementation publicly available to foster future research in this area.

Related papers

• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs [52.50210189669399]
  Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs)<n>We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation.<n>We show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods.
  arXiv  Detail & Related papers  (2026-06-01T03:18:01Z)
• Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering [8.56875523245176]
  Uncertainty Quantification is widely regarded as the primary safeguard for deploying Large Language Models (LLMs) in high-stakes domains.<n>We argue that the field suffers from a category error: mainstream UQ methods for LLMs are just unsupervised clustering algorithms.
  arXiv  Detail & Related papers  (2026-05-19T00:47:02Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy [51.887915969023965]
  We show that modern Large Language Models (LLMs) undergo alignment, leaving a measurable distributional imprint.<n>To mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD)<n>LAPD is a standardized information-weighted statistic based on alignment imprint.
  arXiv  Detail & Related papers  (2026-04-18T09:12:24Z)
• LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs [61.06744611795341]
  Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging.<n>We propose texttttextbfLATA (Laplacian-Assisted Transductive Adaptation), a textittraining- and label-free refinement.<n>texttttextbfLATA sharpens zero-shot predictions without compromising exchangeability.
  arXiv  Detail & Related papers  (2026-02-19T16:45:38Z)
• The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI [0.0]
  This paper introduces a novel auditing framework to quantify latent trait estimation under ordinal uncertainty.<n>The research audits nine leading models across dimensions including Optimization Bias, Sycophancy, and Status-Quo Legitimization.
  arXiv  Detail & Related papers  (2026-02-19T06:56:01Z)
• 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)
• RULERS: Locked Rubrics and Evidence-Anchored Scoring for Robust LLM Evaluation [15.787947727055611]
  We introduce RULERS, a compiler-executor framework that transforms natural language rubrics into executable specifications.<n>RULERS operates by compiling criteria into versioned immutable bundles, enforcing structured decoding with deterministic evidence verification, and applying lightweight Wasserstein-based post-hoc calibration.
  arXiv  Detail & Related papers  (2026-01-13T15:31:42Z)
• Conditional Coverage Diagnostics for Conformal Prediction [47.93989136542648]
  We show that conditional coverage estimation can be a classification problem.<n>We call the resulting family of metrics excess risk of the target coverage (ERT)<n>We release an open-source package for ERT as well as previous conditional coverage metrics.
  arXiv  Detail & Related papers  (2025-12-12T18:47:39Z)
• Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal [31.458406135473805]
  We present UniCR, a unified framework that turns heterogeneous uncertainty evidence into a calibrated probability of correctness.<n>UniCR learns a lightweight calibration head with temperature scaling and proper scoring.<n>Experiments on short-form QA, code generation with execution tests, and retrieval-augmented long-form QA show consistent improvements in calibration metrics.
  arXiv  Detail & Related papers  (2025-09-01T13:14:58Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation [70.62656296780074]
  We propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning, a novel data generation recipe.<n>A data refiner stage in AIDSAFE ensures high-quality outputs by eliminating repetitive, redundant, and deceptive thoughts.<n>Our evaluations demonstrate that AIDSAFE-generated CoTs achieve superior policy adherence and reasoning quality.
  arXiv  Detail & Related papers  (2025-05-27T21:34:40Z)
• WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales [13.807613678989664]
  Methods for nonparametric sequential testing -- especially conformal test martingales (CTMs) and anytime-valid inference -- offer promising tools for this monitoring task.<n>Existing approaches are restricted to monitoring limited hypothesis classes or alarm criteria''
  arXiv  Detail & Related papers  (2025-05-07T17:53:47Z)
• Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction [0.0]
  We propose a model-agnostic uncertainty quantification method that integrates dynamic threshold calibration and cross-modal consistency verification.<n>We show that the framework achieves stable performance across varying calibration-to-test split ratios, underscoring its robustness for real-world deployment in healthcare, autonomous systems, and other safety-sensitive domains.<n>This work bridges the gap between theoretical reliability and practical applicability in multi-modal AI systems, offering a scalable solution for hallucination detection and uncertainty-aware decision-making.
  arXiv  Detail & Related papers  (2025-04-24T15:39:46Z)
• AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented Reasoning [61.28113271728859]
  RAG has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>Standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: textitReasoning Misalignment.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Coverage-Guaranteed Speech Emotion Recognition via Calibrated Uncertainty-Adaptive Prediction Sets [0.0]
  Road rage, often triggered by emotional suppression and sudden outbursts, significantly threatens road safety by causing collisions and aggressive behavior.<n>Speech emotion recognition technologies can mitigate this risk by identifying negative emotions early and issuing timely alerts.<n>We propose a novel risk-controlled prediction framework providing statistically rigorous guarantees on prediction accuracy.
  arXiv  Detail & Related papers  (2025-03-24T12:26:28Z)
• Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency [26.645723217188323]
  Class-Specific Anomaly Detection (CSAD) is an effective novel anomaly detection approach.<n> CSAD evaluates adversarial samples relative to their predicted class distribution, rather than a broad benign distribution.<n>Our evaluation incorporates both anomaly detection rates with SHAP-based assessments to provide a more comprehensive measure of adversarial sample quality.
  arXiv  Detail & Related papers  (2024-12-10T09:17:09Z)
• Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger [76.36315347198195]
  No-Reference Image Quality Assessment (NR-IQA) plays a critical role in evaluating and optimizing computer vision systems.<n>Recent research indicates that NR-IQA models are susceptible to adversarial attacks.<n>We present a novel poisoning-based backdoor attack against NR-IQA (BAIQA)
  arXiv  Detail & Related papers  (2024-12-10T08:07:19Z)
• SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI [58.29510889419971]
  Existing benchmarks for evaluating the security risks and capabilities of code-generating large language models (LLMs) face several key limitations.<n>We introduce a general and scalable benchmark construction framework that begins with manually validated, high-quality seed examples and expands them via targeted mutations.<n>Applying this framework to Python, C/C++, and Java, we build SeCodePLT, a dataset of more than 5.9k samples spanning 44 CWE-based risk categories and three security capabilities.
  arXiv  Detail & Related papers  (2024-10-14T21:17:22Z)
• Post-Contextual-Bandit Inference [57.88785630755165]
  Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-commerce, healthcare, and policymaking. They can both improve outcomes for study participants and increase the chance of identifying good or even best policies. To support credible inference on novel interventions at the end of the study, we still want to construct valid confidence intervals on average treatment effects, subgroup effects, or value of new policies.
  arXiv  Detail & Related papers  (2021-06-01T12:01:51Z)
• Distribution-free uncertainty quantification for classification under label shift [105.27463615756733]
  We focus on uncertainty quantification (UQ) for classification problems via two avenues. We first argue that label shift hurts UQ, by showing degradation in coverage and calibration. We examine these techniques theoretically in a distribution-free framework and demonstrate their excellent practical performance.
  arXiv  Detail & Related papers  (2021-03-04T20:51:03Z)

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.