arXiv AI
Jun 9
Emergent alignment and the projectability of ethical personas
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.
ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs
Related stories
arXiv Machine Learning
Jul 28
TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law
arXiv:2507. 21134v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compliance becomes critical.
arXiv AI
Aug 14
Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
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 AI
Jul 10
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
arXiv:2607. 07766v1 Announce Type: new Abstract: Large language models (LLMs) have become significant providers of mental health support, yet they remain products of an attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires.
Hugging Face Trending Papers
Jul 8
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Large language models (LLMs) have become significant providers of mental health support, yet they remain products of an attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires. Developers' safety responses have been largely reactive, addressing the most visible and acute harms while subtler, longer-term patterns of risk (e.
arXiv Computation and Language
Sep 17
Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant
The paper argues that hallucinations by legal language models should be judged as failures of legal warrant rather than mere factual or citation errors. It defines claim-authority warrant as a context-sensitive relationship between a legal claim and applicable, current authority, and proposes that evaluating warrant can uncover failures missed by traditional accuracy or citation metrics. The authors outline a pilot study, benchmark specifications, and a research agenda to assess whether legal AI systems’ claims are properly licensed by law.
arXiv AI
Sep 7
Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment
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.
arXiv AI
Sep 17
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
The paper introduces PACT, a benchmark designed to evaluate how well enterprise AI assistants follow compliance rules when faced with various pressures such as persistent users or hurried managers. PACT covers twelve regulated domains and forty-eight realistic multi‑turn scenarios, pairing each rule with a shortcut that violates it and applying different pressures across wording and system‑prompt modes. Using PACT, the authors profile six metrics of compliance and aggregate them into a PACTScore, revealing significant variability among 22 LLM models and that even top performers misapply rules 6–10% of the time, with user pressure increasing violations by 65% on average.
arXiv AI
Aug 25
Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards?
arXiv:2608.21409v1 Announce Type: cross Abstract: In medicine, claims remain valid when supported by empirical evidence grounded in stable biological reality. In law, by contrast, truth is contingent...
arXiv AI
Aug 12
Toward a Theory of Value in AI Alignment
arXiv:2608. 10327v1 Announce Type: new Abstract: Can AI systems be aligned to human values?
arXiv AI
Sep 1
Statutory AI: Aligning Large Language Models With Legal Norms
arXiv:2608.28593v1 Announce Type: new Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in...
arXiv AI
Sep 10
How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement
The paper introduces a taxonomy of six user challenge types and a four-layer framework to analyze how large language models respond to user disagreement. Using a dataset of 2,310 challenge scenarios and 32,340 responses from 14 models, the study finds that models often validate users (85%) while still maintaining their original claim (65%). It also reports that models frequently apologize (33%) and transfer authority in advice contexts, with significant variation across model types and task domains.