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: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:2505.11924v4 Announce Type: replace-cross Abstract: Intrinsic moral self-correction refers to the phenomenon where a language model refines its ethical judgments or aligns its outputs purely th...
arXiv:2603.23114v2 Announce Type: replace Abstract: A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We address this gap by i...
The paper introduces a novel framework for assessing second‑order bias in large language models (LLMs), defined as bias in how an LLM judges the acceptability of biased content. Using principles from entitlement epistemology, the authors design a reasoning task that asks LLMs to determine whether a biased text is acceptable for specific demographic groups, and propose two metrics to quantify biased judgments. Experiments on both open‑source and closed‑source models reveal that the task bypasses safety guardrails, uncovers systematic variations across target groups, and demonstrates that models still rely on demographic labels when evaluating bias.
BiasGym is a cost‑effective, generalizable framework that injects specific biases into large language models via token‑based fine‑tuning while keeping the model frozen. It then uses two debiasing methods—Scope and Steer—to identify and suppress or redirect the components responsible for biased behavior. The framework enables consistent bias elicitation, precise localization of bias associations, and targeted debiasing without harming downstream performance, and it has been shown to reduce real‑world stereotypes such as labeling Italians as reckless drivers.
arXiv:2607. 21558v1 Announce Type: new Abstract: Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy as a one-dimensional failure mode.
arXiv:2608.28610v1 Announce Type: new Abstract: Existing LLM moral evaluations typically present models with isolated moral vignettes and elicit a single-shot decision, neglecting a factor known to p...
The paper investigates how large language models encode moral knowledge by training linear probes for each Moral Foundations Theory category and analyzing their geometric relationships. It finds that the model’s moral directions are largely independent yet share a common component, indicating integration rather than collapse into a single detector. This structure is consistent across architectures, emerges early in pre‑training, and reflects corpus statistics rather than the individualizing/binding distinction of Moral Foundations Theory.
arXiv:2605.31328v2 Announce Type: replace Abstract: Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned exam...
arXiv:2408. 05568v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally embedded stereotypes, influence moral judgments, or amplify positive evaluations of majority groups.
The study investigates how large language models encode moral knowledge by training linear probes for each category of Moral Foundations Theory. It finds that the model’s representations for different moral foundations occupy distinct, largely independent dimensions yet share a common positive component, indicating an integrated but nuanced moral structure. This geometry is consistent across model architectures and scales, emerges early in pre‑training, and reflects corpus statistics rather than the individualizing/binding distinction of the theory.
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.