AI Engineer: NLP and Large Language Models Flashcards

What is 'hallucination' in the context of LLMs?

Answer: The model producing plausible-sounding but factually incorrect or fabricated information

LLM hallucination refers to the model confidently generating false, invented information not grounded in training data or retrieved context.

What is the context window in a large language model?

Answer: The maximum number of tokens the model can process in a single input/output sequence

The context window defines the maximum number of tokens (input + output) an LLM can process at once, limiting how much text it can consider.

Which parameter-efficient fine-tuning technique adds low-rank decomposition matrices to model layers instead of updating all weights?

Answer: LoRA (Low-Rank Adaptation)

LoRA freezes pretrained weights and injects trainable low-rank matrices, drastically reducing the number of parameters updated during fine-tuning.

What is 'zero-shot prompting' when using an LLM?

Answer: Asking the model to perform a task without providing any examples in the prompt

Zero-shot prompting asks the LLM to complete a task using only instructions, relying entirely on knowledge from pretraining without in-context examples.

What is 'embedding' in NLP, as used by transformer models?

Answer: A dense, fixed-size vector representation of a token or text that captures semantic meaning

Embeddings map discrete tokens (or entire texts) to dense vectors in a continuous space where semantically similar items are geometrically close.

What is RLHF (Reinforcement Learning from Human Feedback) used for in LLM development?

Answer: Aligning LLM outputs with human preferences and reducing harmful outputs

RLHF uses human preference ratings to train a reward model, then fine-tunes the LLM with RL to produce outputs humans rate as better and safer.