LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability

• URL: http://arxiv.org/abs/2605.31167v1
• Date: Fri, 29 May 2026 11:20:47 GMT
• Title: LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
• Abstract summary: We introduce LLMFACETS (LLM FActuality Cross-EvaluaTion System): an open-source framework with a browser-accessible interface and a plugin architecture.<n>A plugin architecture allows any new metric dataset to be integrated without modifying the evaluation pipeline.<n>We verify the framework through cross-validation of 18 metric implementations against canonical reference libraries.
• Score: 0.937536571362766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Assessing whether Large Language Models outputs are factually grounded, epistemically calibrated, and methodologically reproducible is a prerequisite for responsible AI deployment. Yet auditing LLMs remains inaccessible to non-technical practitioners: existing tools require programming expertise and non-trivial environment setup, and cloud-hosted platforms transmit evaluation data to external services, creating barriers for domain experts and compliance officers legally responsible for AI oversight. We introduce LLM-FACETS (LLM FActuality Cross-EvaluaTion System): an open-source framework with a browser-accessible interface and a plugin architecture, structured around three practitioner profiles (technical experts, domain experts, compliance officers) that mirror the stakeholder categories identified in the EU AI Act and the NIST AI Risk Management Framework. The architecture makes data flows explicit: deterministic metrics (BLEU, ROUGE, BERTScore) run entirely within the self-hosted server with no outbound transmission; LLM-judge metrics contact external APIs explicitly, with users retaining full credential control. The framework operationalizes transparency through three mechanisms: token-level log-probability visualization for epistemic uncertainty, multi-judge consensus to mitigate judge bias, and RAG Triad metrics (Faithfulness, Answer Relevance, Context Relevance) to detect and localize hallucinations. A plugin architecture allows any new metric or dataset to be integrated without modifying the evaluation pipeline. The open-source implementation enables cross-checking across multiple metrics targeting the same property, ensuring reproducibility and decoupling AI accountability from the teams building the systems assessed. We verify the framework through cross-validation of 18 metric implementations against canonical reference libraries.

Related papers

• RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level [0.0]
  Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring.<n>The available readiness frameworks are heterogeneous and difficult to apply automatically.<n>This paper makes two contributions: first, we unify these three frameworks into the Unified AI Readiness Level (AIRL), a nine-level scale built on an environmental evidence ladder.<n>Second, we propose RAIL, a panel-of-experts classifier that operationalizes the scale.
  arXiv  Detail & Related papers  (2026-08-13T16:17:41Z)
• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities [55.23913617185508]
  Agent is an open-source, lightweight, and infrastructure for evaluating Large Language Models (LLMs)-based agents.<n>It organizes the evaluation process around three independent components, namely Benchmark, Harness and Environment.<n>It features a fault-tolerant runtime and comprehensive trajectory analysis tools to transparently diagnose failure modes like reward-hacking.
  arXiv  Detail & Related papers  (2026-07-15T11:11:17Z)
• From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents [69.07911499189129]
  We introduce KAPRO, a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting)<n>Experiments show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings.<n> proprietary and reasoning-oriented models demonstrate more reliable cognitive gating.
  arXiv  Detail & Related papers  (2026-06-09T17:17:08Z)
• VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora [24.484384823423216]
  Existing benchmarks fail to account for information noise, ignore multi-source factual contradictions, and overlook the necessity of grounding visual perception into logical planning.<n>We introduce VeriTrip, a verifiable benchmark designed to meet the increasing demands for agent robustness and reliability.
  arXiv  Detail & Related papers  (2026-05-27T16:14:47Z)
• Chain-of-Authorization: Internalizing Authorization into Large Language Models via Reasoning Trajectories [21.063230721511726]
  Chain-of-Authorization (CoA) framework internalizes authorization logic into Large Language Models' core capabilities.<n>CoA integrates policy execution with task responses, making authorization a causal prerequisite for substantive responses.
  arXiv  Detail & Related papers  (2026-03-24T07:13:01Z)
• Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs [50.075587392477935]
  We conduct the first large-scale empirical study of 705 real-world failures from the open-source DeepSeek, Llama, and Qwen ecosystems.<n>Our analysis reveals a paradigm shift: white-box orchestration relocates the reliability bottleneck from model algorithmic defects to the systemic fragility of the deployment stack.
  arXiv  Detail & Related papers  (2026-01-20T06:42:56Z)
• Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
  Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
  arXiv  Detail & Related papers  (2025-12-23T03:10:09Z)
• WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality [62.43165871914528]
  We introduce WebDevJudge, a systematic benchmark for assessing LLM-as-a-judge performance in web development.<n>WebDevJudge comprises human preference labels over paired web implementations, annotated with structured and query-grounded rubrics.<n>In-depth analysis indicates this gap stems from fundamental model limitations, including failures in recognizing functional equivalence, verifying task feasibility, and mitigating bias.
  arXiv  Detail & Related papers  (2025-10-21T12:16:04Z)
• Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support [1.506501956463029]
  Development of web-based dashboards for risk analysis and decision making often challenged by difficulty in big, multidimensional data.<n>We introduce a generative AI framework that automates the creation of interactive geospatial dashboards from user-defined inputs.
  arXiv  Detail & Related papers  (2025-10-10T10:58:15Z)
• Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework [0.0]
  This article presents a modular, component-based architecture for developing and evaluating AI agents.<n>The system addresses core challenges in data accessibility by enabling non-technical users to interact with complex data warehouses.<n>A cornerstone of the design is its commitment to transparent decision-making, achieved through a multi-layered reasoning framework.
  arXiv  Detail & Related papers  (2025-09-28T23:54:41Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models [76.72220653705679]
  We introduce MCPEval, an open-source framework that automates end-to-end task generation and deep evaluation of intelligent agents.<n> MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines.<n> Empirical results across five real-world domains show its effectiveness in revealing nuanced, domain-specific performance.
  arXiv  Detail & Related papers  (2025-07-17T05:46:27Z)
• HADA: Human-AI Agent Decision Alignment Architecture [0.0]
  HADA is a protocol- and framework reference architecture that keeps both large language model (LLM) agents and legacy algorithms aligned with organizational targets and values.<n>Technical and non-technical actors can query, steer, audit, or contest every decision across strategic, tactical, and real-time horizons.
  arXiv  Detail & Related papers  (2025-06-01T14:04:52Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)

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.