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.
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.
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.
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.
The paper argues that AI alignment depends on a system’s ability to exhibit a coherent moral policy—stable, monotonic, decisive, and Pareto‑viable—rather than on any specific moral standard. The authors test nine large language models across varied moral scenarios and find that none maintain consistent verdicts, with surface‑form changes causing up to 99% shifts in outcomes. This indicates that current LLM agents lack the structural moral competence required for meaningful alignment.
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.
The paper argues that aligning large language models (LLMs) at the level of latent representations—specifically by matching their internal categorization of moral concepts to human prototype-based judgments—improves safety. Current alignment methods that focus on observable responses fail to preserve fine-grained moral categorization, leaving models vulnerable to adversarial rephrasings. By optimizing representational similarity, the authors demonstrate that LLMs can maintain more robust moral categorization and exhibit better adversarial robustness across multiple benchmarks and model sizes.
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
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.
arXiv:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
arXiv:2608. 05166v1 Announce Type: cross Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings.
arXiv:2608. 14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications.
arXiv:2606. 05183v1 Announce Type: cross Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode.