arXiv AI

Decodable But Not Detachable: Training Data Granularity Determines Parametric Modularity in Large Language Models

arXiv:2608. 10214v1 Announce Type: new Abstract: Do large language models contain domain-specific parametric shells: concentrated, causally necessary neuron populations whose removal selectively degrades a target domain while sparing others?

arXiv Machine Learning

Aug 5

Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling

arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.

By Nathan Labiosa, David Buff, Ena Nayak, Erica Donno

llms computer-vision

arXiv AI

Jul 7

Unsupervised Features Mining via Activation Geometry

arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).

By Amit LeVi, Elad David, Max Fomin

llms safety

arXiv Machine Learning

Jul 31

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

arXiv:2607. 28319v1 Announce Type: cross Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs).

By Pere Martra, Eugenio Mart\'inez C\'amara, Alfonso Ure\~na L\'opez

llms efficiency benchmarks safety

arXiv AI

Jul 8

Transformers converge to invariant algorithmic cores

arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.

By Joshua S. Schiffman

llms

arXiv Machine Learning

Jul 14

Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts

arXiv:2607. 09999v1 Announce Type: cross Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved.

By Renuka Oladri, Mohan Vamsi Varadaraju Priya, Jerry Wu

llms efficiency benchmarks

arXiv Machine Learning

1d ago

TokEval: A Tokenizer Evaluation Suite

arXiv:2608. 18062v1 Announce Type: cross Abstract: Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities.

By Clara Meister

llms nlp benchmarks safety

arXiv AI

Jun 3

How Quantization Changes Interpretable Features: A Sparse Autoencoder Analysis of Language Models

arXiv:2606. 03002v1 Announce Type: cross Abstract: Quantization is a standard path to deploying large language models, and a quantized model is typically judged acceptable when its perplexity or downstream accuracy stays close to the full-precision original.

By Evan Duan

llms efficiency safety

arXiv AI

Jun 18

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

arXiv:2604. 13082v2 Announce Type: replace-cross Abstract: Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood.

By Laura Gomezjurado Gonzalez

llms safety

arXiv AI

Jul 22

The Information Shadow: Measuring Structural Limits on What Language Models Can Learn

arXiv:2607. 18305v1 Announce Type: cross Abstract: Some limits on what language models know are not gaps in data coverage but structural properties of learning from text.

By Priyansh Srivastava, Romit Chatterjee

llms benchmarks safety

arXiv AI

Jun 9

Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation

arXiv:2605. 03058v2 Announce Type: replace-cross Abstract: A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms.

By Francesco Sovrano, Gabriele Dominici, Marc Langheinrich

llms efficiency benchmarks safety

arXiv AI

Jul 23

Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Search Inertness in Clue-Rich Completion

arXiv:2607. 19635v1 Announce Type: cross Abstract: Neural solvers are built to deduce, branch, and revise intermediate states.

By Aleksey Komissarov

llms

arXiv AI

Jun 3

Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States

arXiv:2606. 02907v1 Announce Type: cross Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types.

By Subramanyam Sahoo, Vinija Jain, Aman Chadha, Divya Chaudhary

llms benchmarks safety

Related stories