arXiv Machine Learning June 16, 2026 By Noor Islam S. Mohammad, Tamim Sheikh

MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions

Read the original on arXiv Machine Learning →

arXiv:2606. 16562v1 Announce Type: new Abstract: Five years after the discovery of persistent anti-Muslim bias in large language models, most evaluations remain confined to single-turn prompt completion, a setting that no longer reflects how frontier LLMs are deployed.

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

arXiv AI

Aug 7

Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts

arXiv:2608. 06123v1 Announce Type: new Abstract: Measuring political bias in large language models (LLMs) remains challenging as it can manifest through subtle differences in framing, argumentation, and legal reasoning that are difficult to capture with a single metric.

By Massi-Nissa Abboud, Aladin Djuhera, Elena Cabrio, Holger Boche

llms safety

arXiv AI

Jul 17

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs

arXiv:2607. 14888v1 Announce Type: cross Abstract: Finetuning language models on small, curated datasets is standard practice for adapting them to specific policies or domains.

By Robert Graham, Edward Stevinson, Yariv Barsheshat

llms fine-tuning benchmarks safety

arXiv AI

Jul 3

The Agentic Garden of Forking Paths

arXiv:2607. 01507v1 Announce Type: new Abstract: Empirical research rarely admits a unique analysis.

By Jiacheng Miao, Jonathan K Pritchard, James Zou

agents

arXiv AI

Jun 4

PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay

arXiv:2603. 23841v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) are increasingly used as primary sources of information, their potential for political bias may impact their objectivity.

By Rohan Khetan, Ashna Khetan

llms benchmarks safety

arXiv AI

2d ago

BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs

arXiv:2608. 14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications.

By Varsha Ramineni, Hossein A. Rahmani, Jerome Ramos, Karin Sevegnani, Emine Yilmaz

llms safety

arXiv AI

Jun 24

Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War

arXiv:2606. 24391v1 Announce Type: new Abstract: We introduce Age of LLM, a turn-based 1v1 benchmark in which two LLMs face off on a 13x7 grid to destroy the enemy base.

By Arnaud Ricci

llms benchmarks safety

Related stories

Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs

The Agentic Garden of Forking Paths

PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay

BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs

Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War