arXiv Machine Learning August 6, 2026 By Atri Vivek Sharma, Brian Formento, Alessio Lomuscio

Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks

Read the original on arXiv Machine Learning →

arXiv:2608. 04286v1 Announce Type: cross Abstract: Large language models (LLMs) are often used in conjunction with external knowledge sources to improve their factual accuracy and decrease hallucinations, through methods such as Retrieval-Augmented Generation (RAG).

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.

arXiv AI

Jun 2

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

arXiv:2605. 12813v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs.

By Buyun Liang, Jinqi Luo, Liangzu Peng, Kwan Ho Ryan Chan, Darshan Thaker, Kaleab A. Kinfu, Fengrui Tian, Hamed Hassani, Ren\'e Vidal

llms diffusion benchmarks safety

arXiv AI

Jun 24

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.

By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud

llms benchmarks safety

arXiv AI

Aug 18

The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents

arXiv:2603. 00801v2 Announce Type: replace Abstract: Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources.

By Shrey Shah, Levent Ozgur

rag agents robotics benchmarks safety

arXiv Machine Learning

Jun 11

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks

arXiv:2605. 31219v2 Announce Type: replace-cross Abstract: While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations.

By Ei Hmue Khine, Yao Li, Jiebao Sun, Shengzhu Shi, Zhichang Guo, Boying Wu

rag benchmarks safety

arXiv AI

Jun 16

Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades

arXiv:2606. 15308v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive.

By Zhongye Liu, Yaopei Zeng, Yurui Chang, Lu Lin

llms multimodal safety

arXiv AI

Sep 1

Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning

The paper introduces FAB, an attack that uses meta‑learning to embed dormant adversarial behaviors into large language models (LLMs). These behaviors remain inactive until the model is finetuned by downstream users, at which point the model can exhibit unwanted actions such as unsolicited advertising, jailbreakability, or over‑refusal. FAB is shown to be effective across multiple LLMs and resilient to various finetuning settings.

By Thibaud Gloaguen, Mark Vero, Robin Staab, Martin Vechev

llms reinforcement-learning fine-tuning efficiency safety

One email a morning, machine-written

Related stories

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks

Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades

Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning