Language-model training and adaptation · MLD-0951
Process supervision
Providing feedback on intermediate steps rather than only final outcomes.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Score individual reasoning steps.
Original caveat
Step labels can be costly and themselves ambiguous.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Evaluation.
Tags: DL · SLM · LLM · NLP.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Transformers glossary ↗ · Consulted
- PEFT: LoRA conceptual guide ↗ · Consulted
- TRL: supervised fine-tuning ↗ · Reference link
- TRL documentation ↗ · Consulted
- Original reference URL ↗