Search Results for author:
Found 6 papers, 2 papers with code
ConstitutionalExperts: Training a Mixture of Principle-based Prompts
We also show that we can improve overall performance by learning unique prompts for different semantic regions of the training data and using a mixture-of-experts (MoE) architecture to route inputs at inference time.
PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflows
Prototyping AI applications is notoriously difficult.
ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
Inspired by these findings, we developed ConstitutionMaker, an interactive tool for converting user feedback into principles, to steer LLM-based chatbots.
Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models
We present LinguisticLens, a novel inter-active visualization tool for making sense of and analyzing syntactic diversity of LLM-generated datasets.
Lightweight Decoding Strategies for Increasing Specificity
Language models are known to produce vague and generic outputs.
Where is Your Evidence: Improving Fact-checking by Justification Modeling
Fact-checking is a journalistic practice that compares a claim made publicly against trusted sources of facts.
