Paper deep dive
Open-Ethical AI: Advancements in Open-Source Human-Centric Neural Language Models
Sabrina Sicari, Jesus F. Cevallos M., Alessandra Rizzardi, Alberto Coen-Porisini
Year: 2024Venue: ACM Computing SurveysArea: Surveys & ReviewsType: SurveyEmbeddings: 0
Intelligence
Status: not_run | Model: - | Prompt: - | Confidence: 0%
Entities (0)
No extracted entities yet.
Relation Signals (0)
No relation signals yet.
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
A comprehensive survey of open-source methods for building Helpful, Harmless, and Honest (3H) neural language models, covering alignment techniques, benchmarks, and open-source resources across model sizes.
Tags
ai-safety (imported, 100%)alignment-training (suggested, 80%)survey (suggested, 88%)surveys-reviews (suggested, 92%)
Links
- Source: https://dl.acm.org/doi/10.1145/3703454
- Canonical: https://dl.acm.org/doi/10.1145/3703454
Full Text
No full-text extraction is stored for this paper yet.