Using LLMs effectively for academic work

This summary reflects my experience with LLMs over the past several months. I have interacted with Gemini (formerly Bard), ChatGPT (including version 4.5), Perplexity, Claude, and Grok3, along with some use of DeepSeek, Mistral, AllenAI, Leonardo, Midjourney and Copilot.

Every LLM has its strengths and weaknesses, and no one LLM is the best at doing everything for your academic needs. However, the capabilities and functionalities are changing regularly and fast.

Search	Perplexity leads for research; Gemini excels with Google integration. Deepsearch of ChatGPT is excellent in my opinion. Grok DeepSearch is also good.
Hallucination	ChatGPT (DALL-E 3) and Gemini lead in generating stock images. Claude is good at producing charts and graphics for academic purposes. ChatGPT cen refine academic images but is often unreliable.
Reliability	Claude for logic; Perplexity for facts
Deep Search	Perplexity offers it free; Grok, ChatGPT and Gemini shine in paid tiers.
Image Generation	ChatGPT (DALL-E 3) and Gemini lead in generating stock images. Claude is good at producing charts and graphics for academic purposes. ChatGPT can refine academic images but is often unreliable.
Coding	Claude and DeepSeek are top-tier
Video	Gemini has this capability.

Aspect	ChatGPT	Perplexity	Grok	Claude	DeepSeek	Gemini
Search	Paid only, decent	Best, real-time	Real-time, X (twitter) focus	Basic	Good, technical	Excellent, Google
Risk of Hallucination	Moderate	Low	Low	Very Low	Moderate	Moderate
Reliability	High, general	High, research	High, technical	Very High, logic	High, STEM	High, multimodal
Deep Search (Free)	No	Yes	Limited	No	Yes, limited	Yes
Deep Search (Paid)	Yes (Pro)	Yes (Pro)	Yes (Premium+)	No	Yes	Yes (Advanced)
Image Generation	Yes (Paid)	No	Yes (Paid)	No	No	Yes (Paid)
Coding Capability	Strong	Decent	Strong	Exceptional	Exceptional	Strong
Video Generation	No	No	No	No	No	Yes (Paid)

You can use LLMs for

•searching literature, •generating ideas, •blog posts, •social media post, •generating structure for your article, •reviewing your paper or correcting spelling/grammar/structure •summarising •statistical analysis, •critically appraise a paper

•Write an article (you must be careful about generating the whole article for a paper) •generating images (stock image, graph, tables, diagram, or just an absurd image for fun), •testing your understanding of a subject by conversing with you •generating podcast •generating code •generating a short video.

How can you use LLM safely?

•Do not upload confidential data (for example: no patient identifiable data or business intelligence/business critical data) •Follow your organisation’s AI/data policy or your National policy	Although LLM use is considered sessional (the information you upload is not retained after you end the conversation, it might still be reviewed by someone to train the LLM. Also, there is always a potential policy change from the LLM companies, leading to data retention There is always some possibility of data retention if you are using services like ChatGPT scheduled task or perplexity spaces.
•Use your prompts effectively (more on this later) • Cross-check the output (text and reference)	There is always a risk of hallucination (LLM producing information or reference that does not exist). It is important to check the information if you are producing something that is not in the field of imaginative work (writing a story) Any academic work must be checked for its validity. I find expert knowledge is important here. If you are not an expert in that field you risk missing the hallucination. Appropriate prompt can help to some extent, but still cross checking is important
•Check the AI use policy of the organisation •Declare the scope of use of AI in your work	If you are using AI/LLM for serious work (preparing a journal article or business report) your organisation or the publisher may want to know the extent of the use of the AI. Always check what the scope is and comply.
•Beware of the guardrail •Refrain from using AI/LLM for offensive/illegal purpose	There is always a risk of hallucination (LLM producing information or reference that does not exist). It is important to check the information if you are producing something that is not in the field of imaginative work (writing a story) Any academic work must be checked for its validity. I find expert knowledge is important here. If you are not an expert in that field you risk missing the hallucination. Appropriate prompt can help to some extent, but still cross-checking is important

Using prompts effectively for an academic purpose

1. Detailed and Explicit Prompts:

• There is no such thing as a prompt that's "too long." If you have to use a long prompt to get an answer you want, go for it.
• Include context, specific tasks, intended outcomes, and any constraints clearly.

2. Assign a Role or Character to the LLM:

• Clearly define what role the LLM should adopt (e.g., "senior consultant," "editor of a journal," "statistician," "historian"). This significantly influences the nature and depth of responses.
• Example: If you are asking LLM to review an article, write  "Assume you are an editor of a reputed medical journal evaluating a research article. Review this article {name}”
• If you ask LLM "You are Napoleon Bonaparte, analyse the Battle of Gaugamela", you will get a different answer than asking it “You are William Shakespeare – describe the Battle of Gaugamela".

3. Demand factual accuracy explicitly:

• LLMs tend toward generating coherent narratives, occasionally at the expense of factual accuracy. Explicitly instruct the LLM to adhere strictly to factual information.
• LLMs are reluctant to say “no” unless you give it permission to do so.
• Tell it “Provide answers based solely on factual information. Avoid generalisations, assumptions, or extrapolations beyond explicitly stated or verifiable data. If uncertain, explicitly state uncertainty, and if information is not available, say not available."

4. Set clear boundaries and constraints:

Specify clearly what kind of resources and guidelines to use or avoid. For instance:

• “Only cite peer-reviewed journal articles published within the last 10 years, prioritising systematic reviews and meta-analyses.”
• “Primarily use UK guidelines (e.g., NICE, BIA, HIS, BASHH, BHIVA). If no UK guidelines are available, explicitly indicate this and cite European, US, or WHO guidelines.”
• “Explicitly state when using non-peer-reviewed or unofficial sources, clearly indicating their limitations.”

5. Ensure rigorous citation and verification:

Be extra-careful about citation. Citations are a frequent area of inaccuracies or hallucinations. Explicitly instruct the LLM to verify citations and clearly communicate citation details:

• “List citations clearly with authors, title, journal/guideline name, year, DOI or URL. Explicitly confirm that the cited information is accurately located within the provided source (mention page number, section, or heading).”
• “If citation verification fails or is uncertain, explicitly flag this with statements like ‘Citation existence not confirmed,’ ‘Information not found in cited source,’ or ‘Citation accessibility issue.’”

6. Provide a clear structure for answers:

Offer a detailed structure or framework for responses. This significantly improves consistency, completeness, and readability. Example:

• “When describing a bacterial species, provide information under the following structured headings: Classification, Virulence Factors, Laboratory Characteristics (Gram stain, culture media, biochemical tests), Clinical Presentations, Differential Diagnoses, Investigations, and Management/Treatment.”

7. Iterative refinement (Ask the LLM for Help):

If unsure, first ask the LLM to propose an initial outline, structure, or scope for your topic. Example:

• “Suggest a comprehensive outline covering all relevant aspects of bacterial pathogens. Refine this outline based on my feedback.”

8. Precision and language style:

Specify the desired tone and style of writing (e.g., formal academic tone, concise and technical, detailed yet concise). Example:

• "Write in a formal academic style, concise yet detailed, appropriate for postgraduate medical students."
• Or you can ask – guideline style, short summary, summarise in 3 lines, use a language suitable for a lay person..

9. Start a conversation:

• LLM, although not human but remarkably humanlike in its conversational capability. Do not consider it as a machine but assume it as a person who is willing to help you and will never be angry if you ask the same thing hundreds of times (well you can go over your usage limit).
• Start a conversation. If you do not like a part of the answer, suggest it. Ask for refinements. If you like a part – appreciate it. It will take these interactions on board and adjust its answer according to this. However, remember it's memory is sessional, as soon as you close the conversation this small modification will be lost.

10. Make a list of common prompts and store:

•Store your common prompts in a separate place.

• As the LLM's memory is sessional, you can make a big prompt to set the tone of the conversation and then start your interaction.
• Your starting line could be something like – “You are a consultant in the NHS involved in patient care and teaching. You look for answers based solely on factual information. Avoid generalisations, assumptions, or extrapolations beyond explicitly stated or verifiable data. If uncertain, explicitly state uncertainty, and if information is not available, say not available….”

Invite LLM to all your workflows.. (as long as it is safe to do so)..