SYNTHESIS NOTE
Topics›Domain Specialization›this note

Can prompt optimization teach models knowledge they lack?

Explores whether sophisticated prompting techniques can inject new domain knowledge into language models, or if they're limited to activating existing training knowledge.

Synthesis note · 2026-02-21 · sourced from Domain Specialization
How do you build domain expertise into general AI models? How do you navigate synthesis across fragmented research topics?

The knowledge injection survey makes this constraint explicit: prompt optimization "focuses on fully leveraging or guiding the LLM to utilize its internal, pre-existing knowledge." It does not retrieve from external sources. It does not update parameters. It works entirely within the model's existing knowledge distribution.

This is a hard ceiling, not a soft limitation. When a domain requires knowledge that the model was never trained on — proprietary documents, post-training regulations, specialized ontologies, organization-specific processes — no prompting strategy can supply it. The model can reorganize, foreground, or combine what it knows, but it cannot know what it was never trained to know.

The practical consequence shows up in two failure modes. First, models prompted to act as domain experts will confidently apply general-purpose reasoning patterns to domain-specific problems where those patterns don't hold. The prompt activates "medical reasoning" as a behavioral style, not as medical knowledge. Second, prompt performance depends on how thoroughly the domain is represented in pre-training — well-documented domains (clinical guidelines, legal statutes, financial regulations) are more promptable than proprietary or emerging domains.

This makes prompt-only domain specialization a form of retrieval from fixed memory. The memory can be searched more or less skillfully, but it can't be expanded. Every sophisticated prompting technique — few-shot examples, chain-of-thought elicitation, role specification — is fundamentally retrieval from training data, dressed as reasoning.

The implication is that the right question before choosing prompt optimization is not "how should we phrase this prompt?" but "is the required domain knowledge in the model's training distribution?" If yes, prompting is sufficient and efficient. If no, the investment must go into a different injection paradigm — dynamic retrieval, fine-tuning, or adapter layers.

Since Why do specialized models fail outside their domain?, there's a version of the ceiling problem in the opposite direction: models that are fully fine-tuned can know a domain deeply while losing general coverage. Prompt optimization avoids the cliff problem by not modifying parameters — but only by accepting the ceiling problem instead. Every approach involves a trade-off; this one chooses breadth over depth.

Reynolds & McDonell (2021) provide the upstream mechanism: few-shot prompting is "task location in the model's existing space of learned tasks" — not task learning. Alternative 0-shot prompts that communicate task intention through natural language semiotics match or exceed few-shot performance, confirming that the model already has the capability and the prompt's job is to locate it. Meta-prompt programming further extends this: the LLM itself can be prompted to write task-specific prompts, offloading the location search to the model's own understanding of its capabilities.

Inquiring lines that read this note 204

This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.

How do training priors constrain what context information can override? Can prompting inject entirely new knowledge into language models? How can LLM recommenders match or exceed collaborative filtering performance? How effectively do deterministic tools improve language model reasoning on formal tasks? How do neural networks separate factual knowledge from reasoning abilities? Can prompting strategies overcome LLM biases without model fine-tuning? How can persona representations reduce language model variance and improve task accuracy? How do self-generated feedback mechanisms enable effective model learning? How do prompt structure and constraints affect model instruction reliability? How does latent reasoning compare to verbalized chain-of-thought? How do knowledge injection methods compare across cost and effectiveness? How do training data properties shape reasoning capability development? How do adversarial and manipulative prompts attack reasoning models? Can next-token prediction alone produce genuine language understanding? What capability tradeoffs emerge when scaling model reasoning abilities? What actually drives chain-of-thought reasoning improvements in language models? How should inference compute be adaptively allocated based on prompt difficulty? How should dialogue systems best leverage conversation history for retrieval? What makes weaker teacher models effective for stronger student training? How can language models sustain linguistic synchrony and intersubjectivity during dialogue? Do language models learn genuine linguistic structure or just surface patterns? How should retrieval systems optimize for multi-step reasoning during inference? Do language model representations contain causally steerable task-specific features? Why does supervised fine-tuning improve accuracy while degrading reasoning quality? Does reinforcement learning teach reasoning or just when to reason? How should conversational agents balance goal-driven initiative with user control? Why do reasoning models fail at systematic problem-solving and search? Does fine-tuning modify underlying model capabilities or only behavioral outputs? Does alignment training create blind spots in detecting genuine safety threats? What prevents language models from reliably adopting diverse personas? When should retrieval-augmented systems decide to fetch new information? What critical LLM failures do standard benchmarks hide? Why do language models reinforce false assumptions instead of correcting them? Why do benchmark improvements fail to reflect actual reasoning quality? How can models identify insufficient information and respond appropriately without guessing? Which computational strategies best support reasoning in language models? Do base models contain latent reasoning that training can unlock? How can identical external performance mask different internal representations? Can model confidence signals reliably improve reasoning quality and calibration? How can emotions function as reliable information in reasoning and cognitive systems? What pretraining choices and baseline capability constrain reinforcement learning gains? Does domain specialization cause models to lose capabilities elsewhere? Why should disagreement be treated as signal in collaborative reasoning? Why does verification consistently lag behind AI generation? Why do language models struggle with implicit discourse relations? What articulatory information do speech signals carry that text cannot? How do knowledge graphs enable efficient multi-hop reasoning over alternatives? How do evaluation biases undermine LLM quality assessment systems? Why does finetuning cause catastrophic forgetting of model capabilities? How faithfully do LLMs reflect their actual reasoning in outputs and explanations? Do language models perform faithful symbolic reasoning independent of semantic grounding? What limits mechanistic interpretability's ability to characterize models? How should personalization be implemented to improve AI assistant effectiveness? What determines success in training models on multiple tasks? How does example difficulty affect learning efficiency in language models? Is embodied interaction necessary for language meaning and genuine agency? How do interface design choices shape consciousness attribution? When does optimizing for quality undermine the value of diversity? Why does reinforcement learning suppress output diversity compared to supervised fine-tuning? How does memorization interact with learning and generalization? How do language models establish social grounding in human dialogue? What constrains reinforcement learning's ability to expand model reasoning?

Related concepts in this collection 3

This note in its neighbourhood — explore the map, then jump to a related concept in the list below.

Concept map
23 direct connections · 248 in 2-hop network ·dense cluster Open in graph ↗
Can prompt optimization teach models knowledge t… Why do specialized models fail outside their domai… How do knowledge injection methods trade off flexi… Why do language models ignore information in their…

Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph

your link semantically near linked from elsewhere

Related papers in this collection 8

Papers most semantically related to this note, ranked by cosine similarity in the embedding space.

Search by related questions 4

Suggested questions this note speaks to — click to search the collection, or type your own.

Does prompt performance vary by how well training data covers the domain?Why do fine-tuned models fail outside their specialized domains?Can models distinguish between activated knowledge and genuine reasoning?What alternatives exist when required knowledge is absent from training?
Original note title

prompt optimization cannot inject new knowledge — it can only activate knowledge the model already contains