LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
Summary
LaRA is a layer-wise representation analysis framework that detects data contamination in RL post-trained LLMs by measuring geometric deviations across model layers, outperforming output-level baselines.
View Cached Full Text
Cached at: 05/29/26, 03:00 AM
Paper page - LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
Source: https://huggingface.co/papers/2605.29888
Abstract
LaRA is a layer-wise representation analysis framework that detects data contamination in reinforcement learning-post-trained large language models by analyzing geometric deviations across model layers.
Reinforcement learning(RL) post-training has shown to improve reasoning inlarge language models(LLMs). However, there has been little exploration on the problem ofdata contaminationin RL post-training, potentially undermining generalization and evaluation reliability of the training process itself. Existing detection methods primarily rely on output-level signals such as likelihood or entropy, which become unreliable for RL-trained models since RL shapes behavior through trajectory-level rewards rather than token likelihoods. We propose LaRA, alayer-wise representation analysisframework for detecting contamination in RL post-trained LLMs. LaRA introduces three complementary metrics, measuringperturbation sensitivity,directional collapse, andlocal representation rigidityunder controlled perturbations. We find that contamination produces progressivegeometric deviationsacross layers, including amplifiedperturbation sensitivity, strongerdirectional collapse, and enhanced local rigidity. Based on our findings, we also develop a contamination detection protocol that aggregates representation-level deviations across layers and metrics. Experiments on RL-trained reasoning models show that our protocol outperforms existing output-level baselines for contamination detection.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.29888
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.29888 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.29888 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.29888 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
This paper introduces Layer-wise Representation Dynamics (LRD), a framework with three measurement families to analyze how hidden states change across layers in language models. Applied to 31 models on 30 MTEB tasks, LRD reveals architectural differences and enables label-free model selection and inference-time layer pruning.
Auditing Training Data in Domain-adapted LLMs: LoRA-MINT
LoRA-MINT is a methodology for membership inference testing on LLMs fine-tuned with LoRA, achieving high precision in determining if data was used in training, outperforming baselines.
TaRA: Training-Aware Low-Rank Adaptation Initialization
TaRA is a training-aware initialization method for Low-Rank Adaptation (LoRA) that improves gradient fidelity, leading to better fine-tuning performance for large language models across various tasks.
RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
RDP-LoRA uses geometric trajectory analysis and the Ramer-Douglas-Peucker algorithm to automatically select the most impactful layers for parameter-efficient fine-tuning, outperforming full-layer and random LoRA baselines.
Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection
This paper proposes CalibDCD, a calibration framework for feature-based LLM data contamination detection that mitigates feature shifts caused by post-training, improving detection performance by up to 7.0% AUC and 15.0% TPR@5%FPR.