Author

aiterms

What is a hallucination?

A hallucination is when an AI system generates output that sounds plausible but is wrong, unsupported, or made up.

Why it matters

Hallucinations matter because they break trust. If you use a model for search, summarization, coding help, or customer support, a confident but false answer can mislead users, create bugs, or spread bad information.

In practice, teams care about hallucinations whenever they need factual accuracy, source grounding, or reliable behavior. For creative writing, they may be less of a problem; for legal, medical, financial, or operational use, they are a major risk.

How it works

Large language models predict the next token based on patterns in training data and the current prompt. That means they are optimized to produce likely text, not to “know” truth in a human sense.

When the model lacks enough evidence, or when the prompt encourages it to fill gaps, it may still produce a fluent answer. That answer can look authoritative even when it is unsupported. This is especially common when the model is asked for obscure facts, exact citations, or details beyond its context window.

Researchers and practitioners use “hallucination” as a broad term, but the exact definition is not perfectly settled. Some use it for any factual error; others reserve it for confident, ungrounded generation. The common idea is the same: the output is not reliably tied to reality or the provided source material.

Mitigations usually involve grounding the model in retrieved documents, constraining it to answer only from approved sources, using tools for verification, or adding human review for high-stakes tasks.

Tiny concrete example

User: “Who wrote The Great Gatsby and what year was it published?”

Hallucinated answer: “It was written by Ernest Hemingway and published in 1925.”

This sounds confident, but it is wrong. The correct answer is F. Scott Fitzgerald, 1925.

Common pitfalls / when NOT to use it

• Do not assume fluency equals correctness. A polished answer can still be false.
• Do not use an unconstrained model as a source of record for facts, citations, or policy.
• Do not evaluate only by style. A model can be helpful and still hallucinate important details.
• Do not expect hallucinations to disappear entirely. Better prompting and retrieval reduce them, but they do not eliminate them.
• Do not treat every error the same. Sometimes the issue is a simple mistake; sometimes it is unsupported fabrication.

Related terms

• What is a token (and tokenization)?
• What is a transformer?
• What is attention (self-attention)?
• What is temperature in an LLM?
• What is top-p / nucleus sampling?
• What is a mixture-of-experts (MoE) model?
• What is a parameter (model size)?
• What is the KV cache?
• What is grounding?

同じ著者の記事

What is LLM-as-a-judge?

LLM-as-a-judge is the practice of using a large language model to evaluate or rank outputs from another model, system, or workflow, instead of relying only on human reviewers or fixed metrics. It solves a common problem: many AI outputs are hard to score with simple automated checks. If you are judging a summary for usefulness, a chatbot answer for helpfulness, or two candidate responses for preference, exact-match metrics often miss the point. Teams reach for LLM-as-a-judge when they need: **Fa

papoo.work

What is an LLM eval (evaluation)?

An LLM eval, or evaluation, is a test or set of tests used to measure how well a large language model behaves on a task or under a specific set of conditions. If you build with LLMs, you need a way to answer practical questions like: Does this prompt change improve answer quality? Is the model following instructions more reliably? Did a new model version get worse on safety, latency, or factuality? An eval gives you a repeatable way to compare models, prompts, retrieval setups, or fine-tunes. In

papoo.work

What is the KV cache?

The KV cache, or key-value cache, is a memory buffer that stores past attention keys and values so a transformer can generate the next token without recomputing everything from scratch. In autoregressive generation, each new token depends on all previous tokens. Without a KV cache, the model would repeatedly re-run attention over the entire prefix at every step, which is much slower than necessary. You reach for a KV cache when you want faster text generation, lower latency, or higher throughput

papoo.work

What is a parameter (model size)?

A parameter is a learned number inside a model, and “model size” usually means how many of those learned numbers the model has. Parameters are the part of a neural network that gets updated during training, so they determine how much capacity the model has to fit patterns in data. You’ll care about parameter count when you want to compare models, estimate training cost, understand memory use, or get a rough sense of how much hardware a model needs. In practice, “bigger” often means more capable,

papoo.work

What is a mixture-of-experts (MoE) model?

A mixture-of-experts (MoE) model is a neural network that routes each input, or part of an input, to only a small subset of specialized submodels (“experts”) instead of using the whole model every time. MoE models are useful when you want much larger capacity without paying the full compute cost on every token or example. In practice, that means you can scale model size to improve quality while keeping inference and training more efficient than a dense model of similar total parameter count.

papoo.work

What is a token (and tokenization)?

A token is a chunk of text that a language model reads and predicts, and tokenization is the process of splitting text into those chunks. LLMs do not operate directly on raw characters or words; they operate on tokens. That matters because: Input limits are measured in tokens, not characters. Cost and latency are often tied to token count in LLM APIs. Model quality depends on how text is tokenized: the same sentence can become very different token sequences across tokenizers.

papoo.work

What is a transformer?

A transformer is a neural network architecture that processes sequences by using attention to compare each token with the others, making it a flexible foundation for modern language models and many other sequence tasks. Before transformers, many sequence models had to read text step by step, which made long-range dependencies harder to handle and training slower to parallelize. Transformers solve this by letting the model look at many positions in the input at once. In practice, you reach for a

papoo.work

What is attention (self-attention)?

Attention, or self-attention, is a way for a model to decide which other words or tokens in the same input matter most when interpreting each token. Self-attention solves a basic language problem: the meaning of a word often depends on other words nearby or far away. It lets a model build a context-aware representation of each token instead of treating tokens mostly independently or relying only on fixed-size windows. In practice, this is why Transformers work so well for text, code, and other s

papoo.work

What is temperature in an LLM?

Temperature is a sampling setting that controls how random or deterministic an LLM’s next-word choices are when it generates text. Temperature is one of the simplest ways to trade off consistency versus variety. Use a lower temperature when you want stable, repeatable answers: classification-like outputs, structured data, summaries, or code. Use a higher temperature when you want more diversity: brainstorming, creative writing, alternate phrasings, or exploratory chat. In practice, many

papoo.work

What is top-p / nucleus sampling?

Top-p sampling, also called nucleus sampling, is a way to make a language model pick the next token from only the smallest set of likely options whose combined probability reaches a chosen threshold. If you always choose the single most likely next token, model outputs can become repetitive and brittle. If you sample from all tokens, outputs can get noisy and incoherent. Top-p gives you a middle ground: it keeps the model flexible, but trims away the long tail of very unlikely tokens before samp

papoo.work