arXiv AI August 18, 2026 By Tejaswi V. Panchagnula, Bruce Coburn, Bryce J. Dietrich, Robert X. Browning, Edward J. Delp, Fengqing Zhu

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

Read the original on arXiv AI →

arXiv:2608. 14629v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI).

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

Jun 16

Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

arXiv:2606. 15307v1 Announce Type: cross Abstract: Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone.

By Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor, Abul Hasnat, Firoj Alam

llms reinforcement-learning efficiency multimodal benchmarks

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

Jul 23

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.

By Jason Vega, Gagandeep Singh

llms fine-tuning safety

arXiv Computation and Language

Sep 18

The Neutral Mask: How Alignment Training Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

The paper investigates how alignment training, specifically reinforcement learning from human feedback (RLHF), affects the internal partisan structure of a large language model. Using a mechanistic case study on Llama 3.1 8B, the authors find that alignment training does not erase the model’s partisan geometry but compresses its variance, producing consistently balanced, non‑partisan outputs. Sparse autoencoder analysis and feature‑level steering experiments reveal that policy‑encoding features become inactive in the aligned model, indicating a causal disconnect rather than structural removal of partisan knowledge.

By Wendy K. Tam

llms reinforcement-learning safety

arXiv Machine Learning

Jun 4

Data Attribution in Large Language Models via Bidirectional Gradient Optimization

arXiv:2606. 04928v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed across diverse applications, raising critical questions for governance, accountability, and data provenance.

By Fr\'ed\'eric Berdoz, Luca A. Lanzend\"orfer, Kaan Bayraktar, Roger Wattenhofer

llms safety

arXiv AI

Jul 22

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation

arXiv:2606. 25476v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness.

By Abrar Alotaibi, Raed Mughus, Moataz Ahmed

llms nlp safety

One email a morning, machine-written

Related stories

Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

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

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

The Neutral Mask: How Alignment Training Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

Data Attribution in Large Language Models via Bidirectional Gradient Optimization

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation