arXiv Machine Learning June 5, 2026 By Yash Aggarwal, Atmika Gorti, Vinija Jain, Aman Chadha, Krishnaprasad Thirunarayan, Manas Gaur

Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability

Read the original on arXiv Machine Learning →

arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.

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

arXiv AI

Jun 16

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

arXiv:2606. 15507v1 Announce Type: new Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it.

By Ali Dasdan, Manan Shah, W. Russell Neuman, Chad Coleman, Kund Meghani, Safinah Ali

llms reinforcement-learning safety

arXiv AI

Jul 20

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

arXiv:2510. 12229v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear.

By Bianca Raimondi, Daniela Dalbagno, Maurizio Gabbrielli

llms fine-tuning safety

arXiv AI

5d ago

Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales

arXiv:2608. 13250v1 Announce Type: cross Abstract: Normative datasets are often used to train and align AI systems, but the norms they contain can function as action-guiding patterns rather than neutral moral knowledge.

By Long Hoang Nguyen, Brice Valentin Kok-Shun, Guangyu Du, Ali Sunyaev

llms fine-tuning safety

Hugging Face Trending Papers

Jun 17

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.

llms benchmarks safety

arXiv AI

Jun 11

Models That Know How Evaluations Are Designed Score Safer

arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.

By Katharina Deckenbach, Haritz Puerto, Jonas Geiping, Sahar Abdelnabi

fine-tuning benchmarks safety

arXiv AI

Jul 9

Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas

arXiv:2601. 21433v2 Announce Type: replace Abstract: Language models are increasingly consulted on ethically consequential questions, yet the stance a model expresses may not survive a change in framing.

By Katherine Elkins, Jon Chun

llms safety

Related stories

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Models That Know How Evaluations Are Designed Score Safer

Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas