arXiv AI August 12, 2026 By Minsoo Kim, Sungyoung Ji, Kisung Moon, Ilyong Yoon

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.

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 AI.

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 25

POOL: Propagated Uncertainty Over Lookalikes

arXiv:2608.23086v1 Announce Type: new Abstract: Black-box large language models need confidence scores that can separate likely-correct from likely-incorrect outputs, enabling systems to prioritize h...

By Rounak Sharma, Ananya B. Sai, Soumyabrata Pal

llms rag

arXiv AI

Sep 16

When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models

arXiv:2609. 16933v1 Announce Type: cross Abstract: Modern predictive systems expose multiple quantities that are commonly interpreted as measures of confidence.

By Julio C. Amador Diaz Lopez

llms benchmarks

arXiv AI

Jun 11

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

arXiv:2606. 11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution.

By Yuqi Zhang, Di Zhang

llms rag benchmarks safety

arXiv Computation and Language

3d ago

RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures

arXiv:2609.39929v1 Announce Type: cross Abstract: Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and disting...

By Yuyang Wu, Yufeng Du, Hao Peng

llms benchmarks

One email a morning, machine-written

Related stories

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

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

POOL: Propagated Uncertainty Over Lookalikes

When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures