Tag: AI language models
Browse our exclusive articles!
SCRIBE: Enhancing Tool-Using Language Models with Mid-Level Supervision
Discover how SCRIBE improves tool-using language models with structured mid-level supervision, boosting accuracy and multi-step reasoning performance.
Improving Verbal Confidence in Gemma 3 4B LLMs
Explore how confidence-conditioned fine-tuning enhances verbal accuracy in Gemma 3 4B, revealing key lessons on label entropy and output regularization.
Query2Diagram: Generate UML Diagrams from Developer Queries
Query2Diagram uses AI to create relevant UML diagrams from developer queries, improving documentation and codebase understanding efficiently.
Solving Knowledge Conflicts in Hypernetwork LLM Adaptation
Explore innovative methods to fix knowledge conflict failures in hypernetwork-based LLM adaptation, boosting accuracy without extra training.
AIPsy-Affect: Keyword-Free Emotion Test for Language Models
Discover AIPsy-Affect, a 480-item keyword-free battery to accurately interpret emotion in language models without bias from emotional keywords.