Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language Models

• URL: http://arxiv.org/abs/2608.06429v1
• Date: Wed, 05 Aug 2026 20:58:49 GMT
• Title: Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language Models
• Abstract summary: We train a neural network to map error profiles back to perturbation parameters.<n>A fresh model instance with the recovered parameters reproduced the target behavior in 81.4% of cases.<n>This perturbed between low layer recovery and high counterfactual fidelity is consistent with functional redundancy across transformer layers.
• Score: 6.5285083214226125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to produce the observed behavior. In earlier work, we lesioned LLMs to produce error profiles in picture naming, a central task for assessing aphasia, and found that specific lesions produced errors resembling those of individual stroke survivors. Here we ask the inverse question: given an error profile, can the lesion parameters that produced it be recovered, and what does this inverse problem reveal about transformer computation? Lesions in LLaVA-Vicuna 13B were parameterized by layer index, modification percentage, and noise sigma across 4,840 configurations, and error profiles were characterized by a seven-category clinical taxonomy (correct, semantic, unrelated, formal, mixed, neologism, no-response). We trained a multi-task neural network to map error profiles back to perturbation parameters. The problem admitted a partial solution: across 10 independently trained inverse models, modification percentage and noise sigma were recoverable, whereas layer index was recoverable only within a neighborhood. In counterfactual validation, a fresh model instance perturbed with the recovered parameters reproduced the target behavior in 81.4% of cases. This dissociation between low layer recovery and high counterfactual fidelity is consistent with functional redundancy across transformer layers, a property not captured by standard interpretability methods. As an out-of-distribution test, we applied the trained model to picture-naming error profiles from 278 stroke survivors; recovered parameters were syndrome-discriminative, most strongly for perturbation intensity, indicating generalization beyond the training distribution. Counterfactual validation provides a general framework for LLM interpretability claims beyond inverse mapping.

Related papers

• Demystifying Variance in Circuit Discovery of LLMs [51.97489679448601]
  We develop a new circuit discovery method that substantially lessens resampling variance.<n>We show that rephrasing variance arises because prompts with different templates tend to activate different circuits in the model.<n>We argue that sparsity, which has been claimed to form more compact and interpretable task circuits, fails to solve this problem.
  arXiv  Detail & Related papers  (2026-06-15T16:25:07Z)
• Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior [0.0]
  We ask whether human cognitive diversity can be recovered from behavior and transferred to LLM agents.<n>Nous extracts a structured eight-dimension behavioral profile from real Polymarket trading activity and injects it into agents through prompts.<n>We position Nous as measuring the cognitive-monoculture problem and the limits of a prompt-level remedy.
  arXiv  Detail & Related papers  (2026-06-11T08:18:25Z)
• From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data [10.795877029195845]
  A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding.<n>We introduce Multi-Agent Residual In-Context Learning (MARICL)<n>MARICL improves consistently over its base model on all datasets.
  arXiv  Detail & Related papers  (2026-05-21T15:34:08Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors [60.06461883533697]
  We leverage rank-one model editing to establish an attribution-guided model rectification framework.<n>We first distinguish our rectification setting from existing model editing, yielding a formulation that corrects unreliable behavior.<n>To target the primary source of misbehavior, we introduce an attribution-guided layer localization method.
  arXiv  Detail & Related papers  (2026-03-08T01:06:07Z)
• Stroke Lesions as a Rosetta Stone for Language Model Interpretability [6.528508321422611]
  We present the Brain-LLM Unified Model (BLUM) as an external reference structure for evaluating large language models.<n>Using data from individuals with chronic post-stroke aphasia, we trained symptom-to-lesion models that predict brain damage location from behavioral error profiles.<n>BLUM error profiles were sufficiently similar to human error profiles that predicted lesions corresponded to actual lesions in error-matched humans above chance.
  arXiv  Detail & Related papers  (2026-02-03T23:22:37Z)
• Task Shift: From Classification to Regression in Overparameterized Linear Models [5.030445392527011]
  We investigate a phenomenon where latent knowledge is transferred to a more difficult task under a similar data distribution.<n>We show that while minimum-norm interpolators for classification cannot transfer to regression a priori, they experience surprisingly structured attenuation which enables successful task shift with limited additional data.<n>Our results show that while minimum-norm interpolators for classification cannot transfer to regression a priori, they experience surprisingly structured attenuation which enables successful task shift with limited additional data.
  arXiv  Detail & Related papers  (2025-02-18T21:16:01Z)
• Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing [63.20133320524577]
  We show that editing a small subset of parameters can effectively modulate specific behaviors of large language models (LLMs)<n>Our approach achieves reductions of up to 90.0% in toxicity on the RealToxicityPrompts dataset and 49.2% on ToxiGen.
  arXiv  Detail & Related papers  (2024-07-11T17:52:03Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• Semantic Latent Space Regression of Diffusion Autoencoders for Vertebral Fracture Grading [72.45699658852304]
  This paper proposes a novel approach to train a generative Diffusion Autoencoder model as an unsupervised feature extractor. We model fracture grading as a continuous regression, which is more reflective of the smooth progression of fractures. Importantly, the generative nature of our method allows us to visualize different grades of a given vertebra, providing interpretability and insight into the features that contribute to automated grading.
  arXiv  Detail & Related papers  (2023-03-21T17:16:01Z)
• Posterior Collapse and Latent Variable Non-identifiability [54.842098835445]
  We propose a class of latent-identifiable variational autoencoders, deep generative models which enforce identifiability without sacrificing flexibility. Across synthetic and real datasets, latent-identifiable variational autoencoders outperform existing methods in mitigating posterior collapse and providing meaningful representations of the data.
  arXiv  Detail & Related papers  (2023-01-02T06:16:56Z)
• Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to prevent avoidable all-cause readmissions or death [2.198760145670348]
  We developed an inherently interpretable multilevel Bayesian framework for representing variation in regression coefficients. We used the framework to formulate a survival model for using medical claims to predict hospital readmission and death. We trained the model on a 5% sample of Medicare beneficiaries from 2008 and 2011, based on their 2009--2011 inpatient episodes, and then tested the model on 2012 episodes.
  arXiv  Detail & Related papers  (2022-08-28T06:19:32Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)

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.