Contents

Language model

Alanguage model is a probabilistic model of a natural language.^[1] In 1980, the first significant statistical language model was proposed, and during the decade IBM performed ‘Shannon-style’ experiments, in which potential sources for language modeling improvement were identified by observing and analyzing the performance of human subjects in predicting or correcting text.^[2]

Language models are useful for a variety of tasks, including speech recognition^[3] (helping prevent predictions of low-probability (e.g. nonsense) sequences), machine translation,^[4] natural language generation (generating more human-like text), optical character recognition, handwriting recognition,^[5] grammar induction,^[6] and information retrieval.^[7][8]

Large language models, currently their most advanced form, are a combination of larger datasets (frequently using words scraped from the public internet), feedforward neural networks, and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.

Pure statistical models[edit]

Models based on word n-grams[edit]

Exponential[edit]

Maximum entropy language models encode the relationship between a word and the n-gram history using feature functions. The equation is

where ${\displaystyle Z(w_{1},\ldots ,w_{m-1})}$ is the partition function, ${\displaystyle a}$ is the parameter vector, and ${\displaystyle f(w_{1},\ldots ,w_{m})}$ is the feature function. In the simplest case, the feature function is just an indicator of the presence of a certain n-gram. It is helpful to use a prior on ${\displaystyle a}$ or some form of regularization.

The log-bilinear model is another example of an exponential language model.

Skip-gram model[edit]

Formally, a k-skip-n-gram is a length-n subsequence where the components occur at distance at most k from each other.

For example, in the input text:

the rain in Spain falls mainly on the plain

the set of 1-skip-2-grams includes all the bigrams (2-grams), and in addition the subsequences

the in, rain Spain, in falls, Spain mainly, falls on, mainly the, and on plain.

In skip-gram model, semantic relations between words are represented by linear combinations, capturing a form of compositionality. For example, in some such models, if v is the function that maps a word w to its n-d vector representation, then

Neural models[edit]

Recurrent neural network[edit]

Continuous representations or embeddings of words are produced in recurrent neural network-based language models (known also as continuous space language models).^[14] Such continuous space embeddings help to alleviate the curse of dimensionality, which is the consequence of the number of possible sequences of words increasing exponentially with the size of the vocabulary, furtherly causing a data sparsity problem. Neural networks avoid this problem by representing words as non-linear combinations of weights in a neural net.^[15]

Large language models[edit]

Alarge language model (LLM) is a computational model notable for its ability to achieve general-purpose language generation and other natural language processing tasks such as classification. Based on language models, LLMs acquire these abilities by learning statistical relationships from vast amounts of text during a computationally intensive self-supervised and semi-supervised training process.^[16] LLMs can be used for text generation, a form of generative AI, by taking an input text and repeatedly predicting the next token or word.^[17]

LLMs are artificial neural networks that utilize the transformer architecture, invented in 2017. The largest and most capable LLMs, as of June 2024^[update], are built with a decoder-only transformer-based architecture, which enables efficient processing and generation of large-scale text data.

Historically, up to 2020, fine-tuning was the primary method used to adapt a model for specific tasks. However, larger models such as GPT-3 have demonstrated the ability to achieve similar results through prompt engineering, which involves crafting specific input prompts to guide the model's responses.^[18] These models acquire knowledge about syntax, semantics, and ontologies^[19] inherent in human language corpora, but they also inherit inaccuracies and biases present in the data they are trained on.^[20]

Although sometimes matching human performance, it is not clear whether they are plausible cognitive models. At least for recurrent neural networks, it has been shown that they sometimes learn patterns that humans do not, but fail to learn patterns that humans typically do.^[21]

Evaluation and benchmarks[edit]

Evaluation of the quality of language models is mostly done by comparison to human created sample benchmarks created from typical language-oriented tasks. Other, less established, quality tests examine the intrinsic character of a language model or compare two such models. Since language models are typically intended to be dynamic and to learn from data they see, some proposed models investigate the rate of learning, e.g., through inspection of learning curves.^[22]

Various data sets have been developed for use in evaluating language processing systems.^[23] These include:

• Corpus of Linguistic Acceptability^[24]
• GLUE benchmark^[25]
• Microsoft Research Paraphrase Corpus^[26]
• Multi-Genre Natural Language Inference
• Question Natural Language Inference
• Quora Question Pairs^[27]
• Recognizing Textual Entailment^[28]
• Semantic Textual Similarity Benchmark
• SQuAD question answering Test^[29]
• Stanford Sentiment Treebank^[30]
• Winograd NLI
• BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU (Massive Multitask Language Understanding), BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs.^[31] (LLaMa Benchmark)

See also[edit]

References[edit]

Further reading[edit]