Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction

• URL: http://arxiv.org/abs/2605.21653v1
• Date: Wed, 20 May 2026 19:08:38 GMT
• Title: Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction
• Abstract summary: Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
• Score: 51.56484100374058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary. On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures (86-106% of the fine-tuned discrimination ceiling: on RoBERTa-base, raw projection exceeds fine-tuning); on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested. The same axis inverts on non-native ESL writing (AUROC 0.06-0.20) -- a falsifiable prediction unique to the typicality reading. A 24-example frozen probe matches full fine-tuning (0.900 vs 0.895). A closed-form Jacobian predictor parameterises axis-manipulating interventions with R^2 = 1.000 universal, lifts ELECTRA-CE deployment TPR from 0.000 to 0.904 at FPR = 1%, and transfers to three independently-trained third-party RoBERTa detectors at 16/16 oracle-equivalence (57% NYT-FPR reduction on the OpenAI detector). Scope: encoder family; mechanism magnitude HC3-anchored; population-level shared axis with per-text mechanisms varying across architectures. Three operationally distinct probes -- text-surface caps_rate residualisation, geometric signed-epsilon ablation, closed-form text-pair predictor -- agree at cos 0.74/0.81/1.00 across three architectures, confirming observer-invariance. Under matched-TPR-0.90 evaluation, the published intervention zoo (CC, dealign-f2c) is calibration-equivalent across 27 cells (|Delta AUROC| <= 0.0081), and >= 97% of the LoRA->full-FT bias gap on ELECTRA is calibration shift, not learned representation -- the central claim's prediction confirmed.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• Accurate Ensembles, Fragile Narratives: Multi-Scale Stacking and a Fidelity Audit of LLM-Generated Explanations for Credit Risk [0.0]
  Credit scoring increasingly relies on models whose decision logic cannot be read off their parameters.<n>A common proposal closes that gap with a language model: compute feature attributions, hand them to an LLM, and let it write the rationale.<n>We build such a system end to end and test whether the second half of the promise holds.
  arXiv  Detail & Related papers  (2026-08-08T13:22:14Z)
• GLID: Gated Local Intrinsic Dimension Repairs the Blind Spots of Face-Forgery Detectors [4.564848621539382]
  Fine-tuned foundation-model detectors dominate face-forgery benchmarks, yet they stay blind to generator families absent from training.<n>We present GLID, a detector that repairs this blind spot with geometry instead of data.<n>GLID treats the patch tokens of a single image as a sample from a manifold and estimates their local intrinsic dimension (LID) at several depths of a frozen vision transformer.
  arXiv  Detail & Related papers  (2026-07-21T06:52:46Z)
• Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems [47.027290803102666]
  Normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes.<n>We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering.<n>We evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration.
  arXiv  Detail & Related papers  (2026-07-07T10:10:00Z)
• Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics [0.0]
  Detectors for radio-frequency impairments are usually reported with a single AUC measured on the distribution they were tuned on.<n>We ask whether this optimism can be predicted before any out-of-distribution data is seen.
  arXiv  Detail & Related papers  (2026-06-20T14:10:59Z)
• ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models [47.9430487327673]
  ARC-STAR organizes correction into three stages: a global corrector removes broad solver bias, a blockwise local refiner cleans the post-global residual, and, at deployment, a label-free score routes refinement to high-risk blocks under a compute budget.<n>ARC-STAR is the only method that cuts velocity rollout error by at least 36x over raw Poseidon on every cell.
  arXiv  Detail & Related papers  (2026-05-21T09:26:16Z)
• Optimised Support Vector Regression for California Housing Price Prediction: The Critical Role of Feature Engineering and Hyperparameter Tuning [0.0]
  Support Vector Regression has been cited as one of the weakest performers on the California Housing benchmark dataset.<n>This paper examines whether the previously reported performance reflects experimental configuration choices rather than an inherent algorithmic limitation.<n> tuned SVR achieves a test R2 of 0.723, a 0.123-point absolute improvement over the previously reported SVR result.
  arXiv  Detail & Related papers  (2026-05-09T03:58:50Z)
• Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams [0.0]
  Harmful intent is geometrically recoverable from large language model residual streams.<n>We characterise this geometry through six direction-finding strategies.<n>A direction fitted on AdvBench transfers to held-out HarmBench and JailbreakBench with worst-case AUROC 0.96.
  arXiv  Detail & Related papers  (2026-04-20T23:02:37Z)
• LEADER: Learning Reliable Local-to-Global Correspondences for LiDAR Relocalization [44.37632368250295]
  We propose LEADER, a robust LiDAR-based relocalization framework enhanced by a simple, yet effective geometric encoder.<n>Experiments on the Oxford RobotCar and NCLT datasets demonstrate that LEADER outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-13T11:52:29Z)
• Spectral Signatures of Data Quality: Eigenvalue Tail Index as a Diagnostic for Label Noise in Neural Networks [0.0]
  We investigate whether spectral properties of neural network weight matrices can predict test accuracy.<n>Under controlled label noise variation, the tail index alpha of the eigenvalue distribution at the network's bottleneck layer predicts test accuracy with leave-one-out R2 = 0.984 (21 noise levels, 3 seeds per level)<n>We identify the information-processing bottleneck layer as the locus of this signature and connect the observations to the BBP phase transition in random matrix models.
  arXiv  Detail & Related papers  (2026-03-29T21:53:24Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• Multi-Task Deep Learning for Surface Metrology [0.0]
  A reproducible deep learning framework is presented for surface metrology to predict surface texture parameters.<n>Uncertainty is modelled via quantile and heteroscedastic heads with post-hoc conformal calibration to yield calibrated intervals.
  arXiv  Detail & Related papers  (2025-10-23T08:38:18Z)
• Real-time nonlinear inversion of magnetic resonance elastography with operator learning [0.06797079068199119]
  The oNLI framework enables real-time MRE inversion (30,000x speedup) of elastograms with comparable spatial accuracy to NLI.<n>A structural prior mechanism, analogous to Soft Prior Regularization in the MRE literature, was incorporated to improve spatial accuracy.
  arXiv  Detail & Related papers  (2025-10-03T08:55:40Z)
• Group-Adaptive Threshold Optimization for Robust AI-Generated Text Detection [58.419940585826744]
  We introduce FairOPT, an algorithm for group-specific threshold optimization for probabilistic AI-text detectors.<n>We partitioned data into subgroups based on attributes (e.g., text length and writing style) and implemented FairOPT to learn decision thresholds for each group to reduce discrepancy.<n>Our framework paves the way for more robust classification in AI-generated content detection via post-processing.
  arXiv  Detail & Related papers  (2025-02-06T21:58:48Z)
• Robust Representation via Dynamic Feature Aggregation [44.927408735490005]
  Deep convolutional neural network (CNN) based models are vulnerable to adversarial attacks. We propose a method, denoted as Dynamic Feature Aggregation, to compress the embedding space with a novel regularization. An averaging accuracy of 56.91% is achieved by our method on CIFAR-10 against various attack methods.
  arXiv  Detail & Related papers  (2022-05-16T06:22:15Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units [81.53783563025084]
  We propose an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only. HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.
  arXiv  Detail & Related papers  (2021-06-14T14:14:28Z)

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.