arXiv AI June 9, 2026 By Alireza Arbabi, Florian Kerschbaum

Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard

arXiv:2606. 08381v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly released and deployed through opaque development and deployment pipelines, enabling model providers to inject intentional, provider-specific policies without officially announcing them.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 17

ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs

arXiv:2607. 14285v1 Announce Type: cross Abstract: Safety alignment in LLMs aims to align models with human values, but which values take precedence when they conflict?

By Aryan Keluskar, Amrita Bhattacharjee, Huan Liu

llms agents benchmarks safety

arXiv AI

Jun 2

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models

arXiv:2606. 00023v1 Announce Type: cross Abstract: The rapid development of Language Diffusion Models (LDMs) challenges the dominant position of auto-regressive competitors in language processing.

By Yichuan Mo, Yukun Jiang, Yanbo Shi, Mingjie Li, Michael Backes, Yang Zhang, Yisen Wang

diffusion benchmarks safety

arXiv Machine Learning

Jul 22

On the Limits of Support-Preserving Alignment and Bounded Filtering

arXiv:2607. 18295v1 Announce Type: new Abstract: We study whether alignment schemes that reshape a base model's output distribution, combined with bounded safety filters, can drive the probability of harmful behavior to zero in modern large language models.

By Aryan Dutt, Rui Mao, Anupam Chattopadhyay

llms benchmarks safety

arXiv AI

Jul 28

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.

By Yunting Song, Matthew Watson, Peter Grabowski, Jun Qin

llms reinforcement-learning benchmarks safety data-engineering

arXiv AI

Jul 2

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

arXiv:2607. 01208v1 Announce Type: cross Abstract: Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale.

By Shayan Talaei, Abhinav Chinta, Devvrit Khatri, Amin Karbasi, Azalia Mirhoseini, Amin Saberi

llms efficiency safety

arXiv AI

Jun 9

Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models

arXiv:2606. 08451v1 Announce Type: cross Abstract: Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy.

By Arya Shah, Himanshu Beniwal, Mayank Singh, Chaklam Silpasuwanchai

llms nlp benchmarks safety

Related stories

ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models

On the Limits of Support-Preserving Alignment and Bounded Filtering

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models