Learning under noisy supervision is governed by a feedback-truth gap

• URL: http://arxiv.org/abs/2602.16829v1
• Date: Wed, 18 Feb 2026 19:50:56 GMT
• Title: Learning under noisy supervision is governed by a feedback-truth gap
• Abstract summary: We show that when feedback is absorbed faster than task structure can be evaluated, the learner will favor feedback over truth.<n>We test this prediction across neural networks trained with noisy labels (30 datasets, 2,700 runs), human probabilistic reversal learning (N = 292), and human reward/punishment learning with concurrent EEG (N = 25)<n>The gap is a fundamental constraint on learning under noisy supervision; its consequences depend on the regulation each system employs.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When feedback is absorbed faster than task structure can be evaluated, the learner will favor feedback over truth. A two-timescale model shows this feedback-truth gap is inevitable whenever the two rates differ and vanishes only when they match. We test this prediction across neural networks trained with noisy labels (30 datasets, 2,700 runs), human probabilistic reversal learning (N = 292), and human reward/punishment learning with concurrent EEG (N = 25). In each system, truth is defined operationally: held-out labels, the objectively correct option, or the participant's pre-feedback expectation - the only non-circular reference decodable from post-feedback EEG. The gap appeared universally but was regulated differently: dense networks accumulated it as memorization; sparse-residual scaffolding suppressed it; humans generated transient over-commitment that was actively recovered. Neural over-commitment (~0.04-0.10) was amplified tenfold into behavioral commitment (d = 3.3-3.9). The gap is a fundamental constraint on learning under noisy supervision; its consequences depend on the regulation each system employs.

Related papers

• Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up [2.497926557563177]
  False wake-up activations remain a persistent challenge in conversational AI.<n>We introduce the Feedback-Driven Adaptive Self-Correcting Inference Layer (ASCIL)<n>ASCIL re-evaluates wake-up intent before response generation by fusing acoustic embeddings, linguistic cues, device context, and patterns from past misclassifications.
  arXiv  Detail & Related papers  (2026-09-11T06:06:06Z)
• Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks [20.760754362327933]
  We introduce modulo error routing to extend Error Diffusion beyond binary classification.<n>We show that a dual-stream excitatory/inhibitory architecture trained with this method achieves 96.7% on MNIST.<n>In reinforcement learning, we integrate ED with Proximal Policy Optimization (PPO) and evaluate it on continuous-control tasks in Google Brax and on Craftax.
  arXiv  Detail & Related papers  (2026-06-30T14:09:40Z)
• OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training [1.0518862318418603]
  We argue that the Overfitting--Underfitting Indicator (OUI) should be understood as a first practical observable of that internal structure.<n>OUI consistently appears as an early, label-free, activation-based signal that reveals whether a network is entering a poor or promising training regime.
  arXiv  Detail & Related papers  (2026-05-12T05:59:13Z)
• Learning Uncertainty from Sequential Internal Dispersion in Large Language Models [52.29267172760918]
  Uncertainty estimation is a promising approach to detect hallucinations in large language models.<n>Recent approaches commonly depend on model internal states to estimate uncertainty.<n>We present Sequential Internal Variance Representation (SIVR), a supervised hallucination detection framework.
  arXiv  Detail & Related papers  (2026-04-17T06:31:29Z)
• Human Supervision as an Information Bottleneck: A Unified Theory of Error Floors in Human-Guided Learning [51.56484100374058]
  We argue that limitations reflect structural properties of the supervision channel rather than model scale or optimization.<n>We develop a unified theory showing that whenever the human supervision channel is not sufficient for a latent evaluation target, it acts as an information-reducing channel.
  arXiv  Detail & Related papers  (2026-02-26T19:11:32Z)
• Rate or Fate? RLV$^\varepsilon$R: Reinforcement Learning with Verifiable Noisy Rewards [2.0987013818856877]
  Reinforcement learning with verifiable rewards (RLVR) is a simple but powerful paradigm for training LLMs.<n>In practice, however, the verifier is almost never clean-unit tests probe only limited corner cases.<n>We ask a pragmatic question: does the verification noise merely slow down the learning (rate), or can it flip the outcome (fate)?
  arXiv  Detail & Related papers  (2026-01-07T21:31:26Z)
• The Mirror Loop: Recursive Non-Convergence in Generative Reasoning Systems [0.0]
  Recursive self-evaluation without external feedback often yields reformulation rather than progress.<n>We study 144 reasoning sequences across three models (OpenAI GPT-4o-mini, Anthropic Claude 3 Haiku, and Google Gemini 2.0 Flash) and four task families (arithmetic, code, explanation, reflection)<n>We interpret this as evidence for a structural limit on self-correction in generative reasoning.
  arXiv  Detail & Related papers  (2025-10-23T07:53:26Z)
• Peer Effect Estimation in the Presence of Simultaneous Feedback and Unobserved Confounders [16.96064437725128]
  Existing methods either address unobserved confounders while ignoring the simultaneous feedback, or account for feedback but under restrictive linear assumptions.<n>We propose DIG2RSI, a novel Deep learning framework which addresses both simultaneous feedback and unobserved confounding.<n>We prove consistency of our estimator under standard conditions, ensuring recovery of the true peer effect.
  arXiv  Detail & Related papers  (2025-08-05T05:49:49Z)
• Weakly-Supervised Contrastive Learning for Imprecise Class Labels [50.57424331797865]
  We introduce the concept of continuous semantic similarity'' to define positive and negative pairs.<n>We propose a graph-theoretic framework for weakly-supervised contrastive learning.<n>Our framework is highly versatile and can be applied to many weakly-supervised learning scenarios.
  arXiv  Detail & Related papers  (2025-05-28T06:50:40Z)
• The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning [86.19804569376333]
  We show that zero-shot generalization happens very early during instruction tuning.<n>We propose a more grounded training data arrangement framework, Test-centric Multi-turn Arrangement.
  arXiv  Detail & Related papers  (2024-06-17T16:40:21Z)
• REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning [64.08293076551601]
  We propose a novel method of using a learned measure for identifying positive pairs. Our Retrieval-Based Reconstruction measure measures the similarity between two sequences. We show that the REBAR error is a predictor of mutual class membership.
  arXiv  Detail & Related papers  (2023-11-01T13:44:45Z)
• An Empirical Study of Implicit Regularization in Deep Offline RL [44.62587507925864]
  We study the relation between effective rank and performance on three offline RL datasets. We identify three phases of learning that explain the impact of implicit regularization on the learning dynamics.
  arXiv  Detail & Related papers  (2022-07-05T15:07:31Z)
• Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap [64.60460828425502]
  We propose a new guarantee on the downstream performance of contrastive learning. Our new theory hinges on the insight that the support of different intra-class samples will become more overlapped under aggressive data augmentations. We propose an unsupervised model selection metric ARC that aligns well with downstream accuracy.
  arXiv  Detail & Related papers  (2022-03-25T05:36:26Z)
• A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning [8.188575923130662]
  We argue that notable lessons from open set recognition, the identification of statistically deviating data outside of the observed dataset, and the adjacent field of active learning, are frequently overlooked in the deep learning era. Our results show that this not only benefits each individual paradigm, but highlights the natural synergies in a common framework.
  arXiv  Detail & Related papers  (2020-09-03T16:56:36Z)
• Learning from Failure: Training Debiased Classifier from Biased Classifier [76.52804102765931]
  We show that neural networks learn to rely on spurious correlation only when it is "easier" to learn than the desired knowledge. We propose a failure-based debiasing scheme by training a pair of neural networks simultaneously. Our method significantly improves the training of the network against various types of biases in both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2020-07-06T07:20:29Z)
• Overfitting in adversarially robust deep learning [86.11788847990783]
  We show that overfitting to the training set does in fact harm robust performance to a very large degree in adversarially robust training. We also show that effects such as the double descent curve do still occur in adversarially trained models, yet fail to explain the observed overfitting.
  arXiv  Detail & Related papers  (2020-02-26T15:40:50Z)

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.