Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code

• URL: http://arxiv.org/abs/2607.24797v2
• Date: Thu, 30 Jul 2026 03:05:57 GMT
• Title: Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code
• Abstract summary: We show that a decoder-only large language model drives both from one autoregressive path optimized on text.<n>We ask how entangled it is, comparing an input-side reading code'' $mathbfW_E$ with an output-side writing code'' $mathbfW_U$.<n>For minimal pairs the alexia analogue is empty by theorem; greedy production implies a vocabulary-wide argmax, so it wins the pairwise ranking.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the literate human brain, reading and writing doubly dissociate: a ventral decoding route (pure alexia) and a fronto-parietal encoding route (pure agraphia), sharing a partial orthographic core. A decoder-only large language model (LLM) drives both from one autoregressive path optimized on text (a \emph{cultural} invention, not an evolved instinct). We ask how entangled it is, comparing an input-side ``reading code'' $\mathbf{W}_{E}$ with an output-side ``writing code'' $\mathbf{W}_{U}$ via an index $\mathcal{E}\in[0,1]$ (CKA, Procrustes residual, mutual $k$-NN) calibrated against an independent-init floor and tied ceiling. On GPT-2, OPT and Pythia (14M--1.4B), untied models hold one \emph{coupled but sub-ceiling} code ($\mathcal{E}=0.23$--$0.35$, far above floor) on a non-monotonic couple-then-differentiate trajectory, $\mathbf{W}_{U}$ drifting $\sim$3.2$\times$ farther than $\mathbf{W}_{E}$ in every decile. Equally informative is a negative: the matching behavioural test, that comprehension and production fail together rather than dissociate, cannot be run. For minimal pairs the alexia analogue is empty by theorem: greedy production implies a vocabulary-wide argmax, so it wins the pairwise ranking. Differential-damage indices are not scale-identified: heavy-tailed damage makes linear standardizations collapse onto their larger term, and the rank transform fixing this is bounded, so its null saturates. Both scores also contain the target's log-probability, which alone explains most of their variance and manufactures the apparent coupling. We withdraw a coupling statistic, a cross-level bridge and a separation measure. In a model reading and writing off one next-token distribution, no output-side pair isolates either ability: entanglement needing no index to see. By analogy, not homology, this situates LLMs in the space of possible minds.

Related papers

• One Inverse Step is a Convex Program: Bayes-Limit Calibration of Diffusion Inversion [0.0]
  One implicit DDIM inversion step is the cheapest probe of whether a pretrained diffusion model encodes local manifold geometry.<n>The Fermi window conflicts with the model's own training support by $3.6$-$5.6times$, and the trained Hessian-Lipschitz constant is $2$-$12%$ of the curvature the law reads.<n>Finally the unconditional ceiling $_t_max(mathrmsym,J)le1$, from $mathrmCov(x_0mid x_t)succeq0$
  arXiv  Detail & Related papers  (2026-08-24T11:01:54Z)
• Directional Contextual Representations for Dependency Relations: Why Cross-Direction Pairing Fails [22.49571926071395]
  We show that pairing a token's forward state against a emphcandidate's backward state (cross-direction'' pairing, $F_i$ vs. $B_j$) consistently emphunderperforms same-direction pairing, and the penalty emphgrows, not shrinks, with token distance, both paired-bootstrap significant.
  arXiv  Detail & Related papers  (2026-08-21T00:50:25Z)
• Optimal Rates for Learning with Monotone Adversaries [7.053805156684374]
  A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice.<n>Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not exchangeable.<n>Larsen, Pabbaraju, and Shetty, who introduced this model, show that empirical risk minimization attains expected error $O((d/n)log(n/d))$ for classes of VC dimension $d$.
  arXiv  Detail & Related papers  (2026-08-06T17:45:32Z)
• Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings [0.5076419064097734]
  Serial verification gates are a core reliability primitive in LLM harnesses.<n>A candidate answer is returned only if $k$ verifier calls all accept it.<n>This note gives a minimal such theory.
  arXiv  Detail & Related papers  (2026-07-15T14:58:37Z)
• Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation [0.0]
  Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment.<n>We give a provable account on recurring-regime streams.
  arXiv  Detail & Related papers  (2026-06-19T09:30:55Z)
• The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations [50.43168858368539]
  Large language models confidently produce outdated answers, and no existing method can detect them.<n>We show this is not an engineering failure but a structural one: temporal drift is encoded as a direction in the residual stream geometrically to both correctness and uncertainty.
  arXiv  Detail & Related papers  (2026-05-09T22:27:31Z)
• Reliable Abstention under Adversarial Injections: Tight Lower Bounds and New Upper Bounds [16.636823007179082]
  We study online learning in the adversarial injection model introduced by [Goel et al. 2017].<n>We prove a matching $(sqrtT)$ lower bound for VC dimension $1$, establishing a sharp separation between the two information regimes.<n>We introduce a potential-based framework driven by emphrobust witnesses, small subsets of labeled examples that certify predictions remaining resilient to adversarial contamination.
  arXiv  Detail & Related papers  (2026-02-23T18:30:48Z)
• Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games [60.871651115241406]
  A considerable chasm has been looming for decades between theory and practice in zero-sum game solving through first-order methods.<n>We propose a new scale-invariance and parameter-free variant of PRM$+$, which we call IREG-PRM$+$.<n>We show that it achieves $T-1/2$ best-iterate and $T-1$ optimal convergence guarantees, while also being on par with PRM$+$ on benchmark games.
  arXiv  Detail & Related papers  (2025-10-06T00:33:20Z)
• Learning in an Echo Chamber: Online Learning with Replay Adversary [13.758101623622105]
  We introduce a learning-theoretic framework: Online Learning in the Replay Setting.<n>A closure-based learner makes at most $mathrmExThD(mathcalH)$ mistakes against any adaptive adversary.<n>For adversaries, we prove a similar bound for every intersection-closed class.
  arXiv  Detail & Related papers  (2025-09-29T17:50:24Z)
• Statistical Learning under Heterogeneous Distribution Shift [71.8393170225794]
  Ground-truth predictor is additive $mathbbE[mathbfz mid mathbfx,mathbfy] = f_star(mathbfx) +g_star(mathbfy)$.
  arXiv  Detail & Related papers  (2023-02-27T16:34:21Z)
• Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes [62.90204655228324]
  We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic and a value-optimistic solver.
  arXiv  Detail & Related papers  (2022-10-20T21:32:01Z)
• Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model [50.38446482252857]
  Two-player zero-sum Markov games are arguably the most basic setting in multi-agent reinforcement learning. We develop a learning algorithm that learns an $varepsilon$-approximate Markov NE policy using $$ widetildeObigg. We derive a refined regret bound for FTRL that makes explicit the role of variance-type quantities.
  arXiv  Detail & Related papers  (2022-08-22T17:24:55Z)
• Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP [76.94328400919836]
  We show how to construct variance-aware confidence sets for linear bandits and linear mixture Decision Process (MDP) For linear bandits, we obtain an $widetildeO(mathrmpoly(d)sqrt1 + sum_i=1Ksigma_i2) regret bound, where $d is the feature dimension. For linear mixture MDP, we obtain an $widetildeO(mathrmpoly(d)sqrtK)$ regret bound, where
  arXiv  Detail & Related papers  (2021-01-29T18:57:52Z)

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.