Glossary
AI decision-model glossary, A to Z
60 terms, each defined in plain language with links to the deeper explainers.
Swiss-hosted inference. Nothing you send is ever stored.Swiss data residency
60 pages · press / to search
A
- Decisions in productionAbstentionAbstention is when an automated system deliberately declines to decide, usually because its confidence is too low, and hands the case to a person or another system.Read
- Laya & the APIAct probabilityAct probability is Laya's estimate of whether an answer is safe to act on rather than escalate; its maintainers report it does not yet carry a usable signal.Read
- Benchmarks & datasetsAG NewsAG News is a public benchmark in which models sort news articles into four topics (World, Sports, Business, Sci/Tech), widely used to compare text classifiers.Read
- Calibration & scoringAutoregressive modelAn autoregressive model, such as a GPT-style chatbot, writes its output one word-piece at a time, with each new piece depending on everything it has written so far.Read
B
- Benchmarks & datasetsBanking77Banking77 is a public benchmark of 13,083 banking customer queries sorted into 77 closely related intents, which makes it a hard test for classifiers.Read
- Speed & servingBatchingBatching means processing several requests or questions together in one pass through a model, which lowers the cost per item and raises the total work done.Read
- Calibration & scoringBrier scoreThe Brier score rates probability forecasts by the average squared gap between the predicted probability and what actually happened; lower is better.Read
C
- Calibration & scoringCalibrationA model is calibrated when its confidence can be taken at face value: of all the answers it gives at 80% confidence, about 80% turn out to be right.Read
- Laya & the APIChoice questionA choice question asks Laya to pick one answer from a list you define, such as a department, and returns the pick plus a probability for every option.Read
- Models & architectureContext windowThe context window is the maximum amount of text, counted in tokens, that a model can read in one go; anything longer is cut off or must be split.Read
D
- Decisions in productionData residencyData residency is the requirement or promise that data is stored and processed only within a specific country or region, such as Switzerland.Read
- Calibration & scoringDecoder modelA decoder model reads text left to right and predicts the next word-piece, which is the design behind text-generating AI such as GPT-style chatbots.Read
E
- Models & architectureEncoder modelAn encoder model reads a whole text at once, looking both forwards and backwards, to understand it rather than to write new text; BERT-family models are encoders.Read
- Decisions in productionEntropy-based confidenceEntropy-based confidence measures how concentrated a probability distribution is on a single answer, from 1 (completely sure) to 0 (every option equally likely).Read
- Decisions in productionEscalationEscalation hands a case from an automated decision to a more capable handler, such as a human, a senior team or a larger model, when risk or uncertainty is high.Read
- Calibration & scoringExpected calibration error (ECE)Expected calibration error (ECE) is a single number for how far a model's stated confidence is from how often it is actually right, where lower is better.Read
F
- TrainingFew-shot learningFew-shot learning teaches a model a task from just a handful of labelled examples, either shown in the request or used for a small amount of extra training.Read
- TrainingFine-tuningFine-tuning is extra training of an existing model on your own labelled examples so that it specialises in your task, usually becoming more accurate.Read
G
- TrainingGaussian exploration noiseGaussian exploration noise is small random jitter added to a model's outputs during training so it tries slightly different answers and learns which score better.Read
- Speed & servingGPU inferenceGPU inference means running a trained AI model on a graphics card, whose thousands of parallel cores answer requests far faster than an ordinary processor.Read
H
- Decisions in productionHallucinationA hallucination is when a text-generating AI states something fluent and plausible that is not supported by its input or by fact, such as an invented category.Read
- Decisions in productionHuman-in-the-loopHuman-in-the-loop means people review, correct or approve some of an automated system's decisions, and their feedback is used to improve it over time.Read
I
- Speed & servingInference latencyInference latency is how long a model takes to answer one request, from sending the input to getting the result back, which is the wait users and agents feel.Read
- Decisions in productionIntent classificationIntent classification works out what a person wants from their message, such as a refund or a password reset, so it can be routed or answered correctly.Read
J
L
- Laya & the APILanguage routingLanguage routing automatically sends each request to the model best suited to its language; Laya chooses between its English and multilingual models this way.Read
- Laya & the APILayaLaya is an open-source (Apache-2.0) decision model by Convai Innovations that answers typed questions about text with probabilities, without generating text.Read
- Calibration & scoringLog scoreThe log score grades a forecast by the logarithm of the probability it gave to what actually happened, so confident wrong answers are punished very heavily.Read
- Models & architectureLogitsLogits are the raw scores a model gives each option before they are turned into probabilities; only the gaps between them matter, not their absolute size.Read
M
- Laya & the API[MASK] tokenThe [MASK] token is a special placeholder that stands in for a hidden word during training; Laya reuses it to mark the spot where each answer option is scored.Read
- Models & architectureMasked language model (MLM)A masked language model learns language by filling in blanks: words in a sentence are hidden and the model guesses them from the words on both sides.Read
- Benchmarks & datasetsMASSIVEMASSIVE is Amazon's dataset of about one million voice-assistant requests in 51 languages, used to test how well models understand intents across languages.Read
- Laya & the APImmBERTmmBERT is a multilingual text-understanding model in the ModernBERT style, trained on 1,800+ languages; Laya's multilingual model is built on mmBERT-base.Read
- Laya & the APIModernBERTModernBERT is a 2024 modernised version of the BERT text-understanding model that reads longer inputs faster; Laya's English model is built on ModernBERT-large.Read
N
- Benchmarks & datasetsNatural language inference (NLI)Natural language inference (NLI) is deciding whether one sentence follows from, contradicts, or is unrelated to another, and it powers many zero-shot classifiers.Read
- Decisions in productionnFADP (Swiss Federal Act on Data Protection)The nFADP is Switzerland's revised Federal Act on Data Protection, in force since 1 September 2023, which sets the rules for handling personal data about people.Read
- Models & architectureNon-autoregressive modelA non-autoregressive model produces its whole answer in one step, instead of writing it out word by word the way a chatbot does, which makes it much faster.Read
- Laya & the APINoul questionA noul question is a yes/no check: Laya returns the probability that a statement about your text is true, such as 'the customer asks for a refund'.Read
O
P
- Speed & servingp50 / p95 latencyp50 and p95 latency are the response times that half and 95% of requests beat, describing the typical wait and the slow tail that users actually notice.Read
- Calibration & scoringProper scoring ruleA proper scoring rule grades probability forecasts so that the only way to get the best expected score is to report what you honestly believe.Read
R
- Calibration & scoringRanked probability score (RPS)The ranked probability score (RPS) grades forecasts on ordered scales, so predicting 'high' when the truth is 'medium' costs less than predicting 'low'.Read
- Laya & the APIReinforcement learningReinforcement learning trains a model by trial and reward rather than by copying labelled answers; Laya uses it to reward honest probabilities.Read
- Calibration & scoringReliability diagramA reliability diagram is a chart of a model's stated confidence against how often it was actually right, where an honest model follows the diagonal line.Read
- TrainingReward shapingReward shaping adjusts or combines the rewards used in reinforcement learning to steer a model toward the behaviour you want and help it learn faster.Read
- Calibration & scoringRLCDRLCD (Reinforcement Learning for Calibrated Decisions) is how Laya is trained: it is rewarded for honest probabilities, so overstating confidence never pays.Read
S
- Laya & the APIScore questionA score question asks Laya to place something on an ordered scale you describe, such as low, medium or high urgency, and returns the expected level.Read
- Laya & the APIScript detectionScript detection works out which writing system a text uses, such as Latin, Cyrillic, Devanagari or Chinese characters; Laya uses it to pick the right model.Read
- Models & architectureSoftmaxSoftmax is the step that turns a model's raw scores for each option into probabilities that are all positive and add up to 100%.Read
- Calibration & scoringSpherical scoreThe spherical score is a bounded, honesty-rewarding way to grade probability forecasts, so one confident miss cannot wreck the total as it can with the log score.Read
- Decisions in productionSystem 1System 1 is fast, automatic, intuitive thinking; in AI the term describes models that decide in one quick pass instead of reasoning step by step.Read
- Decisions in productionSystem 2System 2 is slow, deliberate reasoning; in AI the term describes models that spend extra time and compute, such as writing out steps, before they answer.Read
T
- Calibration & scoringTemperature scalingTemperature scaling is a one-number fix applied after training that makes a model's probabilities less over-confident, without changing which answer it picks.Read
- Speed & servingThroughputThroughput is how much work a model server finishes per second, such as questions answered, and depends on the hardware, batching and length of the inputs.Read
- Calibration & scoringTokenizerA tokenizer chops text into the small word-pieces (tokens) a model actually reads, and its vocabulary decides which languages and scripts the model handles well.Read
- Laya & the APITyped decisionsTyped decisions are answers limited to a format you declare up front (a pick from a list, a level on a scale, or yes/no) and returned with probabilities.Read
V
X
Z
- Decisions in productionZero data retentionZero data retention means a service processes what you send and then discards it, never saving the content to a database, log or training set.Read
- Models & architectureZero-shot classificationZero-shot means a model handles a task it was never specifically trained for, using only the labels or descriptions you give it at the time of the request.Read