arXiv Machine Learning July 21, 2026 By Yide Ran, Jianwen Xie, Minghui Wang, Wenjin Zheng, Denghui Zhang, Chuan Li, Zhaozhuo Xu

Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation

Read the original on arXiv Machine Learning →

arXiv:2604. 16197v2 Announce Type: replace Abstract: Data attribution and valuation are critical for understanding data-model synergy for Large Language Models (LLMs), yet existing gradient-based methods suffer from scalability challenges on LLMs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Jul 13

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms fine-tuning multimodal safety

arXiv Machine Learning

Jun 4

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations

arXiv:2606. 05165v1 Announce Type: new Abstract: Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data.

By Rishit Dagli, Abir Harrasse, Luke Zhang, Florent Draye, Amirali Abdullah, Bernhard Sch\"olkopf, Zhijing Jin

llms benchmarks

arXiv AI

Jul 28

Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

arXiv:2607. 23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference.

By Dhruvil S, Fenil Sojitra, Ravirajsinh Chauhan

llms fine-tuning safety

arXiv Machine Learning

Jun 8

Inferring the Size of Large Language Models From Popular Text Memorization

arXiv:2605. 29223v3 Announce Type: replace Abstract: The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary reference point for interpreting capabilities and costs -- largely undisclosed.

By Ivica Nikolic

llms

arXiv Computation and Language

Sep 1

Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled

arXiv:2505.12196v2 Announce Type: replace Abstract: The impressive linguistic abilities of large language models (LLMs) have recommended them as models of human sentence processing, with some conject...

By Yi-Chien Lin, Hongao Zhu, William Schuler

llms

arXiv AI

Sep 1

Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models

arXiv:2605.24564v2 Announce Type: replace Abstract: Backtesting large language models (LLMs) on historical financial data is unreliable when their pre-training data include the evaluated events. An L...

By Weixian Waylon Li, Mengyu Wang, Tiejun Ma

llms benchmarks safety

One email a morning, machine-written

Related stories

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations

Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

Inferring the Size of Large Language Models From Popular Text Memorization

Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled

Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models