An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers

• URL: http://arxiv.org/abs/2607.17696v1
• Date: Mon, 20 Jul 2026 08:44:31 GMT
• Title: An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers
• Abstract summary: We develop an adjoint-sensitivity framework for positional influence in causal residual Transformers.<n>We state boundary advantages under independently checkable energy, correlation, and local-channel bounds.
• Score: 1.4180331276028662
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We develop an adjoint-sensitivity framework for positional influence in causal residual Transformers and separate unconditional analytic results from conditional boundary-shape conclusions. The principal unconditional theorem is the residual-to-depth-flow estimate for layer controls converging in $L^1$, complemented by a finite-token-to-Volterra attention estimate that explicitly controls the first cells near the causal endpoint. We define a normalized adjoint-energy influence density and derive its exact evolution along full-batch gradient flow. The adjoint admits an exact generator-term decomposition into residual transmission, nonlocal Volterra, and local channels, including all covariance cross terms. Causal masking can amplify early-position sensitivity and residual identity paths can transmit a right-localized terminal bias, but neither mechanism alone forces a U-shaped profile. We therefore state boundary advantages under independently checkable energy, correlation, and local-channel bounds; these conditions are sufficient rather than necessary. Finite-token influence balancing, positional reweighting, and task-aligned observability are presented as diagnostics or regularizers with explicit differentiation requirements, computational costs, and limitations. Controlled simulations illustrate that each intervention controls its designated surrogate, while observability balance or outer-loop reweighting need not monotonically reduce the influence-based Lost-in-the-Middle diagnostic.

Related papers

• Characterizing Heterogeneous Rates in Finite Mixture Estimation via Partial Optimal Transport [88.55403215843967]
  Voronoi-based partial optimal transport (VPOT) for obtaining refined local and global convergence guarantees for the maximum likelihood estimator of the mixing measure.<n>Results hold in arbitrary fixed dimension without requiring mixing proportions to be uniformly bounded away from zero or prior knowledge of the true number of mixture components.
  arXiv  Detail & Related papers  (2026-09-15T04:32:53Z)
• Finite-Sample Metric Non-Collapse for Geometrically Supervised Latent World Models in Control [0.0]
  We establish a finite-sample learning-to-control theory for geometrically supervised latent models of nonlinear deterministic systems.<n>We introduce an encoder-only local--global metric hinge that enforces directional resolution and separated-state discrimination.<n>A modular deterministic transfers the learned certificates to trajectory, finite-horizon cost, learned-cost-head, and corollary guarantees, while a validated finite-net result enables sharper model-specific certification.
  arXiv  Detail & Related papers  (2026-08-07T14:25:33Z)
• Discrete energy as an exact label-free training objective for finite-element surrogates [0.8125368885437911]
  This note records, with proofs, the identities that make this signal exact for linear elastostatics.<n>Label-free discrete-energy minimisation and supervised regression in the stiffness norm have the same unique minimiser and identical gradients at every point.
  arXiv  Detail & Related papers  (2026-08-05T22:15:38Z)
• Feed-Forward Steering in Transformer Residual Dynamics [4.109803241412197]
  We extend attention-only Transformer residual directions by incorporating the feed-forward network (FFN) term as a local steering field on each token state.<n>The resulting theory predicts that the tangential component of the FFN field is necessary for motion in residual-direction space.<n>As a practical application, layers with small commutator defects can be approximately parallelized with only a modest increase in loss.
  arXiv  Detail & Related papers  (2026-08-03T11:15:31Z)
• A Mean-Field Analysis of Multi-Head Self-Attention under Cross-Entropy Training [0.0]
  This paper develops a mean-field theory for a single-layer causal multi-head self-attention model trained by cross-entropy minimization.<n>In the infinite-head limit, the averaged attention logits define a risk functional on probability measures, whose first variation generates a nonlinear Wasserstein gradient-flow equation.<n>We study the long-time behavior of the PDE: energy dissipation, convergence to the stationary set under compactness, convergence to a single stationary measure under topological or Kurdyka--ojasiewicz assumptions, and explicit convergence rates under gradient-domination conditions.
  arXiv  Detail & Related papers  (2026-06-09T06:38:27Z)
• Self-Consistent Generative Paths via Admissible Random Variational Transport [14.74009385288423]
  We study a complementary question: when is a generated probability path self-consistent?<n>We define a self-consistent generative path as a random fixed point of admissible local variational transport corrections.<n>The resulting theory turns endpoint matching into path self-consistency testing.
  arXiv  Detail & Related papers  (2026-06-08T02:56:06Z)
• Trajectory-Aware Node Contributions and the Limits of Static Controllability [0.0]
  "emergent contribution" is a measure of a node's dynamical leverage.<n>"EC" reduces exactly to average controllability in the linear, time-invariant limit.<n>We place five estimated real systems from several domains within this phase space.
  arXiv  Detail & Related papers  (2026-06-02T02:56:36Z)
• The conditional-mean barrier: From deterministic regression to conditional distribution learning [6.160113667162026]
  This tutorial develops a self-contained module centered on the conditional-mean barrier.<n>Adding latent randomness to a squared-loss predictor collapses it back to the conditional mean.<n>We briefly organize common distributional objectives, including negative log-likelihood, moment and observable matching, variational objectives, adversarial divergences, and score matching.
  arXiv  Detail & Related papers  (2026-05-27T07:31:42Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective [60.45433515408158]
  We show that long Chain-of-Thought (CoT) serves as a decisive decision-maker for the top option but fails to function as a granular distribution calibrator for ambiguous tasks.<n>We observe a distinct "decoupled mechanism": while CoT improves distributional alignment, final accuracy is dictated by CoT content.
  arXiv  Detail & Related papers  (2026-01-06T16:26:40Z)
• Verifying Closed-Loop Contractivity of Learning-Based Controllers via Partitioning [52.23804865017831]
  We address the problem of verifying closed-loop contraction in nonlinear control systems whose controller and contraction metric are both parameterized by neural networks.<n>We derive a tractable and scalable sufficient condition for closed-loop contractivity that reduces to checking that the dominant eigenvalue of a symmetric Metzler matrix is nonpositive.
  arXiv  Detail & Related papers  (2025-12-01T23:06:56Z)
• Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations [57.179679246370114]
  We identify the distribution of random perturbations that minimizes the estimator's variance as the perturbation stepsize tends to zero.<n>Our findings reveal that such desired perturbations can align directionally with the true gradient, instead of maintaining a fixed length.
  arXiv  Detail & Related papers  (2025-10-22T19:06:39Z)
• Localisation in quasiperiodic chains: a theory based on convergence of local propagators [68.8204255655161]
  We present a theory of localisation in quasiperiodic chains with nearest-neighbour hoppings, based on the convergence of local propagators. Analysing the convergence of these continued fractions, localisation or its absence can be determined, yielding in turn the critical points and mobility edges. Results are exemplified by analysing the theory for three quasiperiodic models covering a range of behaviour.
  arXiv  Detail & Related papers  (2021-02-18T16:19:52Z)

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.