instruction following
Instruction following in AI refers to the capability of models to understand and execute commands or requests given in natural language, often used in chatbots and virtual assistants.
- AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios
- CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
- Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
- Checklists Are Better Than Reward Models For Aligning Language Models
- Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance
- Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
- Lookahead Routing for Large Language Models
- MergeBench: A Benchmark for Merging Domain-Specialized LLMs
- Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
- SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback