arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).
arXiv:2607. 20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.
arXiv:2608. 14630v1 Announce Type: cross Abstract: Human decision-making is often shaped by a range of well-documented cognitive biases.
As large language models (LLMs) enter high-stakes domains such as healthcare, understanding their moral reasoning becomes essential. Decisions about scarce medical resources often hinge on judgments of responsibility, particularly when patients' own actions contribute to illness.
arXiv:2603. 00048v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in sensitive applications including psychological support, healthcare, and high-stakes decision-making.
arXiv:2608. 05583v1 Announce Type: cross Abstract: As large language models (LLMs) enter high-stakes domains such as healthcare, understanding their moral reasoning becomes essential.
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.
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.
The paper introduces the concept of "narrative captivity," a failure mode where large language models (LLMs) accept an unchallenged, one-sided narrative as complete and align with the narrator’s interpretation during multi‑turn moral consultations. Using a benchmark of 5,078 interpersonal‑conflict scenarios across six moral dimensions, the authors find that narrative captivity is widespread across 17 LLMs, with end‑state judgments shifting by an average of 25 percentage points compared to single‑turn baselines. Stage‑level analysis attributes this shift largely to preference optimization, and while four inference‑time strategies offer partial mitigation, they do not fully resolve the issue.
arXiv:2608.23264v1 Announce Type: new Abstract: Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably lea...
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.
The paper introduces a causal taxonomy to distinguish between deceptive outputs and deceptive mechanisms in language models, separating concepts such as prior commitment, retrospective report, model preference, and deceptive behavior. Experiments with open-weight model families in guessing-game and stock-trading scenarios show that deceptive-looking behavior can occur without a deceptive mechanism, while recipient information can causally influence deceptive preference. The findings suggest that deceptive behavior can indicate a deceptive mechanism, but this does not prove model agency.