The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

• URL: http://arxiv.org/abs/2605.26778v1
• Date: Tue, 26 May 2026 09:48:51 GMT
• Title: The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
• Abstract summary: We introduce Computational Reality Monitoring to address the attribution blind spot.<n> CRM operationalizes a principle adapted from cognitive science's reality monitoring framework.<n>It detects whether pretraining exposure leaves a measurable internal trajectory signature.
• Score: 22.202409807556517
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually governs generation -- a prerequisite for any high-stakes deployment. The standard assumption, that context-consistent output implies context-governed output, breaks when the retrieved document overlaps with the model's pretraining data: the model can produce faithful-looking text entirely from parametric memory, and both pathways yield indistinguishable output. We name this failure the attribution blind spot and introduce Computational Reality Monitoring (CRM) to address it. CRM operationalizes a principle adapted from cognitive science's reality monitoring framework: comparing internal representations with and without context reveals membership-conditioned representational divergence that output-level monitors systematically miss. CRM does not certify which source an individual generation used; it detects whether pretraining exposure leaves a measurable internal trajectory signature, establishing a necessary substrate for source attribution. Across nine model variants spanning three families, this divergence concentrates in architecture-specific layer patterns, receives converging support from block-level noise intervention, and generalizes across tasks and datasets while collapsing on domain-confounded benchmarks. The attribution blind spot is measurable and partially addressable: internal representations carry a diagnostic signal invisible at the output level, establishing a foundation for systems whose internal awareness of evidence provenance governs their external behavior.

Related papers

• The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models [0.0]
  Evaluations of generative language models frequently interpret observable behavioral traits, such as political stance, brand inclination, and normative framing, as manifestations of model weights, post-training alignment, or prompting.<n>We examine inference-time framing bias: systematic steering of generated text toward institutional, ideological, or commercial frames without requiring changes to the underlying model parameters.<n>We argue that governance of generative systems must increasingly distinguish between auditing a model and auditing the deployed system that ultimately speaks.
  arXiv  Detail & Related papers  (2026-08-25T15:05:19Z)
• DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection [0.0]
  We develop a unified post-hoc detection framework that treats copyright infringement evidence as a counterfactual conditional distribution shift.<n>A protected target is suspicious when the model's behavior under aligned conditions would change measurably if that target were included in, or removed from, the training process.<n>The framework is instantiated for ridge-regularized linear regression, conditional diffusion models, autoregressive language models, and multimodal models.
  arXiv  Detail & Related papers  (2026-07-24T07:00:44Z)
• Diagnosing Failure Modes of Shared-State Collaboration in Resource-Constrained Visual Agents [2.5754366051855837]
  We study failure modes of collaborative reasoning with weak learners through the lens of noise accumulation.<n>We introduce CoSee, an auditing framework that formalizes the read-write-verify loop to trace information flow in document visual question answering.<n>We identify two dominant failure modes: Noise Reinforcement, where ungrounded notes are reused as evidence, and Policy Collapse, where added context shifts the model toward under-specified workspaces.
  arXiv  Detail & Related papers  (2026-05-29T14:29:56Z)
• The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation [18.83395586542378]
  Multimodal Large Language Models (MLLMs) are increasingly integrated with Retrieval-Augmented Generation (RAG)<n>We identify and formalize the phenomenon of recorruption, where the introduction of even perfectly accurate "oracle" context causes a capable model to abandon an initially correct prediction.<n>We propose Bottleneck Attention Intervention for Recovery (BAIR), a parameter-free, inference-time framework that restores visual saliency and applies position-aware penalties to textual distractors.
  arXiv  Detail & Related papers  (2026-05-07T02:27:04Z)
• K$α$LOS finds Consensus: A Meta-Algorithm for Evaluating Inter-Annotator Agreement in Complex Vision Tasks [4.297070083645049]
  We propose K$$LOS, a unified meta-algorithm that generalizes the "Localization First" principle to dataset quality evaluation.<n>By resolving spatial correspondence before assessing agreement, our framework transforms complex-categorical problems into nominal reliability.
  arXiv  Detail & Related papers  (2026-03-28T08:54:05Z)
• Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models [60.25003813232697]
  We propose Adaptive Retrieval-Augmented Masked Diffusion (ARAM) as a training-free adaptive guidance framework for Masked Diffusion Models (MDMs)<n>ARAM calibrates the guidance scale during denoising according to the Signal-to-Noise Ratio (SNR) of the distributional shift induced by retrieved context.<n>Experiments on multiple knowledge-intensive QA benchmarks show that ARAM improves overall QA performance over competitive RAG baselines.
  arXiv  Detail & Related papers  (2026-03-18T12:54:50Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• Hallucination Detection and Mitigation in Large Language Models [0.0]
  Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law.<n>Their tendency to hallucinate, generating factually incorrect or unsupported content, poses a critical reliability risk.<n>This paper introduces a comprehensive framework for hallucination management, built on a continuous improvement cycle driven by root cause awareness.
  arXiv  Detail & Related papers  (2026-01-14T23:19:37Z)
• Towards Unsupervised Causal Representation Learning via Latent Additive Noise Model Causal Autoencoders [1.9732490977700972]
  Unsupervised representation learning seeks to recover latent generative factors.<n>Disentangling causal variables from observational data is impossible without supervision.<n>We propose the Latent Additive Noise Model Causal Autoencoder (LANCA) as a strong inductive bias for unsupervised discovery.
  arXiv  Detail & Related papers  (2025-12-15T10:52:30Z)
• SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling [50.66950115630554]
  Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs)<n>However, retrieval and multimodal fusion obscure content provenance, rendering existing membership inference methods unable to reliably attribute generated outputs to pre-training, external retrieval, or user input, thus undermining privacy leakage accountability.<n>We propose the first Source-aware Membership Audit (SMA) that enables fine-grained source attribution of generated content in a semi-black-box setting with retrieval control capabilities.
  arXiv  Detail & Related papers  (2025-08-12T17:32:24Z)
• Context-Informed Grounding Supervision [102.11698329887226]
  Context-INformed Grounding Supervision (CINGS) is a post-training supervision in which the model is trained with relevant context prepended to the response.<n>Our experiments demonstrate that models trained with CINGS exhibit stronger grounding in both textual and visual domains.
  arXiv  Detail & Related papers  (2025-06-18T14:13:56Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Parallel Key-Value Cache Fusion for Position Invariant RAG [55.9809686190244]
  Large Language Models (LLMs) are sensitive to the position of relevant information within contexts.<n>We introduce a framework that generates consistent outputs for decoder-only models, irrespective of the input context order.
  arXiv  Detail & Related papers  (2025-01-13T17:50:30Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)

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.