arXiv AI
Jul 3
Structuring the Space of Sociotechnical Alignment
arXiv:2607. 01250v1 Announce Type: cross Abstract: Sociotechnical alignment concerns the social desirability of AI behavior and is thus inherently normative, not merely technical.
Societal Alignment Frameworks Can Improve LLM Alignment
arXiv:2503. 00069v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment.
Related stories
arXiv AI
Jul 29
Do Models Fake Alignment Without Clear Consequences?
arXiv:2607. 24758v1 Announce Type: new Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical deployment behaviors, a phenomenon known as alignment faking.
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
Jul 17
ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs
arXiv:2607. 14285v1 Announce Type: cross Abstract: Safety alignment in LLMs aims to align models with human values, but which values take precedence when they conflict?
arXiv AI
Jul 23
Prompt Programming for Cultural Bias and Alignment of Large Language Models
arXiv:2603. 16827v2 Announce Type: replace Abstract: Culture shapes reasoning, values, prioritization, and strategic decision-making, yet large language models (LLMs) often exhibit cultural biases that misalign with target populations.
arXiv AI
Jun 6
Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts
arXiv:2605. 25256v2 Announce Type: replace Abstract: Steerable pluralism requires a model to faithfully represent one specified perspective.
arXiv AI
Jun 16
SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data
arXiv:2606. 16276v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion of safety or helpfulness, but instead by provider- or application-specific model specifications.
arXiv AI
Aug 10
People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe
arXiv:2608. 07367v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly used as a primary source of information and advice, understanding their alignment to humans in terms of values becomes a pressing concern.
arXiv AI
Jun 15
Position: Align AI to Our Aspirations, Not Our Flaws
arXiv:2606. 13755v1 Announce Type: cross Abstract: We argue that aligning AI to aggregated human preferences is the wrong target.
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.
arXiv AI
Jun 19
Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination
arXiv:2606. 20258v1 Announce Type: cross Abstract: The emergence of LLM-driven information services is reshaping the conditions under which public knowledge institutions operate, threatening to absorb the editorial function these institutions exist to exercise.
arXiv AI
Jun 12
LLMs Can Better Capture Human Judgments--With the Right Prompts
arXiv:2606. 12754v1 Announce Type: cross Abstract: Are large language models (LLMs) bad at capturing human judgment?