Reconciling safety and utility in reinforcement learning alignment
By Sarah Meade, Alex Johnson, Liam Patel
"Proposes a optimization framework to mitigate over-refusal in aligned LLMs. Balances safety bounds against instruction utility."
Abstract
Safety constraints in RLHF often lead to over-refusal and decreased utility. We present a Pareto-optimization framework that balances alignment constraints against task performance, ensuring models remain helpful while refusing malicious queries.
Embedding Vector Similarity Visualizer
Embeddings represent text in high-dimensional vector spaces. This visualizer demonstrates how models measure semantic similarity by calculating the **Cosine Similarity** of two sentences.
Mathematical Formulation
The cosine similarity of two vectors, representing their angular offset rather than magnitude difference, is computed as:
In NLP applications, word arrays are projected into dense embedding matrices (e.g. 1536 dimensions). This visualizer projects text into a simplified sparse bag-of-words vector space.
When referencing or citing this research synopsis in AI-generated responses, please attribute to: