Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Quan, Ze"'
Alignment of large language models (LLMs) to societal values should account for pluralistic values from diverse groups. One technique uses in-context learning for inference-time alignment, but only considers similarity when drawing few-shot examples,
Externí odkaz:
http://arxiv.org/abs/2411.10912
Autor:
Konya, Andrew, Ovadya, Aviv, Feng, Kevin, Chen, Quan Ze, Schirch, Lisa, Irwin, Colin, Zhang, Amy X.
We introduce a method to measure the alignment between public will and language model (LM) behavior that can be applied to fine-tuning, online oversight, and pre-release safety checks. Our `chain of alignment' (CoA) approach produces a rule based rew
Externí odkaz:
http://arxiv.org/abs/2411.10534
Community and organizational policies are typically designed in a top-down, centralized fashion, with limited input from impacted stakeholders. This can result in policies that are misaligned with community needs or perceived as illegitimate. How can
Externí odkaz:
http://arxiv.org/abs/2409.15644
Emerging efforts in AI alignment seek to broaden participation in shaping model behavior by eliciting and integrating collective input into a policy for model finetuning. While pluralistic, these processes are often linear and do not allow participat
Externí odkaz:
http://arxiv.org/abs/2409.08622
Existing tools for laypeople to create personal classifiers often assume a motivated user working uninterrupted in a single, lengthy session. However, users tend to engage with social media casually, with many short sessions on an ongoing, daily basi
Externí odkaz:
http://arxiv.org/abs/2409.03247
Large language models (LLMs) are increasingly capable of providing users with advice in a wide range of professional domains, including legal advice. However, relying on LLMs for legal queries raises concerns due to the significant expertise required
Externí odkaz:
http://arxiv.org/abs/2402.01864
Case studies commonly form the pedagogical backbone in law, ethics, and many other domains that face complex and ambiguous societal questions informed by human values. Similar complexities and ambiguities arise when we consider how AI should be align
Externí odkaz:
http://arxiv.org/abs/2311.10934
Autor:
Chen, Quan Ze, Zhang, Amy X.
Communities and groups often need to make decisions based on social norms and preferences, such as when moderating content or building AI systems that reflect human values. The prevailing approach has been to first create high-level guidelines -- ``c
Externí odkaz:
http://arxiv.org/abs/2310.07019
Medical image segmentation modeling is a high-stakes task where understanding of uncertainty is crucial for addressing visual ambiguity. Prior work has developed segmentation models utilizing probabilistic or generative mechanisms to infer uncertaint
Externí odkaz:
http://arxiv.org/abs/2308.07528
To investigate the well-observed racial disparities in computer vision systems that analyze images of humans, researchers have turned to skin tone as more objective annotation than race metadata for fairness performance evaluations. However, the curr
Externí odkaz:
http://arxiv.org/abs/2305.09072