ProvenAI: Provenance-Native Traces of Evidence in Generated Answers
Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source meaningfully shaped the output. This paper introduces ProvenAI, a framework that decomposes transparency in multi-hop question answering into three independently measurable layers: answer correctness, citation fidelity against benchmark supporting evidence, and per-document influence under leave-one-resource-out intervention. Targeting the HotpotQA distractor benchmark through a seven-stage pipeline covering data normalisation, retrieval indexing, citation-aware answer generation, attribution auditing, ablation-based influence estimation, batch evaluation, and interactive inspection, ProvenAI evaluates 7,405 validation examples drawn from a canonical corpus of 509,300 passages. The system achieves 53.53% answer accuracy alongside a mean citation-fidelity score of 71.55%, and a worked example surfaces what we call the citation-influence gap: a clean citation audit co-occurring with a profile in which one cited source registers only weak influence while seven uncited sources demonstrably shift the output. We formalise the relationship between the implemented surface proxy and a token-level KL-divergence target through a stated faithfulness condition, ground the framework in causal-mediation analysis and database-provenance theory, and discuss how the three measurement layers compose with cryptographic provenance architectures emerging in autonomous scientific discovery. ProvenAI establishes that meaningful transparency in retrieval-grounded QA requires traceable links across retrieved, cited, and behaviourally influential evidence as three distinct, independently measured layers.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-hop Question AnsweringAnswer GenerationSimilar Papers 제목 키워드 기반
Reasoning Provenance for Autonomous AI Agents: Structured Behavioral Analytics Beyond State Checkpoints and Execution Traces
As AI agents transition from human-supervised copilots to autonomous platform infrastructure, the ability to analyze their reasoning behavior across populations of investigations becomes a pressing infrastructure require…
From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
Large language model (LLM)-based agents are evolving from passive text generators into autonomous systems capable of planning, tool use, retrieval, memory access, environmental interaction, and multi-agent collaboration.…
READER: Robust Evidence-based Authorship Decoding via Extracted Representations
As agentic applications increasingly route user tasks through official and third-party LLM APIs, provenance becomes an operational question: which model generated a given black-box response? We study Dynamic Black-Box LL…
Safeguarding LLM Agents from Misalignment through Provenance Analysis
As LLM agents gain increasing access to powerful tools, ensuring that their actions are aligned with the user's intent becomes critical. When an agent's proposed tool invocation deviates from the user's intent -- a pheno…
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, databases, clinical records, and formulary tools. Standard factuality metrics…