supervised fine-tuning ↔ Large Language Models

Relations (1)

related 2.32 — strongly supporting 4 facts

Supervised fine-tuning is a specific method used to enhance or train Large Language Models, as described in [1], [2], [3], and [4].

Facts (4)

Sources

Hallucination Causes: Why Language Models Fabricate Facts mbrenndoerfer.com M. Brenndoerfer · mbrenndoerfer.com 3 facts

claimInstruction-following datasets used for supervised finetuning often have thin coverage of rare query types, meaning models receive little practice on the specific queries where they are most likely to hallucinate.

claimSupervised finetuning (SFT) datasets, which are created by human annotators, can introduce factual errors into large language models because human annotators make mistakes, have knowledge gaps, and may produce authoritative-sounding text on topics outside their expertise.

claimLarge language models trained on supervised finetuning data learn the style of confident, well-structured prose because human annotators tend to produce such responses when demonstrating ideal answers.

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 1 fact

referenceThe integration of Knowledge Graphs into Large Language Models can be categorized into three types based on the effect of the enhancement: pre-training, reasoning methods (including supervised fine-tuning and alignment fine-tuning), and model interpretability.