Hugging Face Trending Papers August 3, 2026

Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?

Read the original on Hugging Face Trending Papers →

A benchmark score means nothing without knowing what a trivial method achieves and what the best possible method could achieve. We construct both bounds for a task with a rare kind of ground truth: predicting which sentences a crowd of readers -- highlighting for their own purposes, unpaid, uninstructed, and blind to each other -- marked in 120 web documents.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jul 7

Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)

arXiv:2607. 04223v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why.

By Mohamed Aly Bouke

rag nlp benchmarks safety

arXiv AI

Jul 17

Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect

arXiv:2607. 14111v1 Announce Type: cross Abstract: Can small language models detect and report on perturbations their own internal activations?

By Ely Hahami, Ishaan Sinha, Lavik Jain

llms fine-tuning benchmarks safety

arXiv AI

Aug 12

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

arXiv:2608. 11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is \emph{fragile} under perturbation of its attention pathways.

By Minsoo Kim, Sungyoung Ji, Kisung Moon, Ilyong Yoon

llms benchmarks

arXiv AI

2d ago

Split the Labor: Separating Evidence Interpretation from Decision Aggregation

arXiv:2608. 14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt.

By Zhelun Wu

llms

arXiv AI

Jun 16

Intelligence Is Not the Bottleneck: Validating an LLM First-Pass Manuscript Score Against Peer-Review Outcomes

arXiv:2606. 15887v1 Announce Type: cross Abstract: Large language model (LLM) systems are increasingly proposed to assist peer review, yet most evaluations judge the prose of machine-generated review text, not the validity of the numeric score a system assigns.

By Costa Georgantas

llms fine-tuning

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

Related stories

Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)

Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

Split the Labor: Separating Evidence Interpretation from Decision Aggregation

Intelligence Is Not the Bottleneck: Validating an LLM First-Pass Manuscript Score Against Peer-Review Outcomes

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