36 accepted papers
The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-training merely surfaces this knowledge. The SAH, however, lacks a precise definition, which has led to (i) different and seemingly orthogonal arguments suppo…
Recent works have proven tokenisation to be NP-complete. However, their proofs' constructions rely on tokenisation being applied to inputs with alphabets of unbounded cardinality, which does not accurately reflect the real world. Indeed, since practical applications of tokenisers involve fixed-size…
Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite near-perfect performance on high-resource languages, existi…
Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser—which maps character-strings to subwords—should not affect the probability assigned to the underlying character-string; in practice, i…
In this paper, we investigate the convergence of language models (LMs) trained under different random seeds, measuring convergence as the expected per-token Kullback–Leibler (KL) divergence across seeds. By comparing LM convergence as a function of model size and training checkpoint, we identify a f
The concept of causal abstraction got recently popularised to demystify the opaque decision-making processes of machine learning models; in short, a neural network can be abstracted as a higher-level algorithm if there exists a function which allows us to map between them. Notably, most interpretabi…
In spoken communication, information is transmitted not only via words, but also through a rich array of non-verbal signals, including prosody—the non-segmental auditory features of speech. Do these different communication channels carry distinct information? Prior work has shown that the informatio…
In this work, we prove the NP-completeness of two variants of tokenisation, defined here as the problem of compressing a dataset to at most 𝛿 symbols by either finding a vocabulary directly (_direct_ tokenisation), or selecting a sequence of merge operations (_bottom-up_ tokenisation).
This paper argues that the relationship between lexical identity and prosody—one well-studied parameter of linguistic variation—can be characterized using information theory. We predict that languages that use prosody to make lexical distinctions should exhibit a higher mutual information between wo…
Understanding memorisation in language models has practical and societal implications, e.g., studying models’ training dynamics or preventing copyright infringements.Prior work defines memorisation as the causal effect of training with an instance on the model’s ability to predict that instance. Thi…
Language models (LMs) estimate a probability distribution over strings in a natural language; these distributions are crucial for computing perplexity and surprisal in linguistics research. While we are usually concerned with measuring these values for words, most LMs operate over subwords. Despite…
Text generation, a component in applications such as dialogue systems, relies heavily on decoding algorithms that sample strings from a language model distribution. Traditional methods like top-k and top-𝜋 decoding locally normalise the model’s output, which can significantly distort the original di…
Tokenisation is a core part of language models (LMs). It involves splitting a character sequence into subwords which are assigned random indices before being served to the LM. However, this process—while typically lossless—may lead to less efficient LM training, because it removes character-level in…
Surprisal theory posits that the cognitive effort required to comprehend a word is determined by its contextual predictability, quantified assurprisal. Traditionally, surprisal theory treats words as distinct entities, overlooking any potential similarity between them. Giulianelli et al. (2023) addr…
Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 over all finite strings. However, in some pathological cases, probability mass can “leak” onto the set of infinite sequen…
After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, making it difficult to estimate the probability distribution over next tokens. Yet around this point, these models have id…
The left-corner transformation (Rosenkrantz and Lewis, 1970) is used to remove left recursion from context-free grammars, which is an important step towards making the grammar parsable top-down with simple techniques. This paper generalizes prior left-corner transformations to support semiring-weigh…
Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity over fine-tuning due to its simplicity and improved out-of-domain generalization, and because extensive evidence shows t…
Surprisal theory (Hale, 2001; Levy, 2008) posits that a word’s reading time is proportional to its surprisal (i.e., to its negative log probability given the proceeding context). Since we are unable to access a word’s ground-truth probability, surprisal theory has been empirically tested using surpr…
Sampling-based decoding strategies are widely employed for generating text from probabilistic models, yet standard ancestral sampling often results in text that is degenerate or incoherent. To alleviate this issue, various modifications to a model’s sampling distribution, such as top-p or top-k samp…
A good automatic evaluation metric for language generation ideally correlates highly with human judgements of text quality. Yet, there is a dearth of such metrics, which inhibits the rapid and efficient progress of language generators. One exception is the recently proposed Mauve. In theory, Mauve…
Prosody---the suprasegmental component of speech, including pitch, loudness, and tempo---carries critical aspects of meaning. However, the relationship between the information conveyed by prosody vs. by the words themselves remains poorly understood. We use large language models (LLMs) to estimate h…
Zipf (1935) posited that wordforms are optimized to minimize utterances' communicative costs. Under the assumption that cost is given by an utterance's length, he supported this claim by showing that words' lengths are inversely correlated with their frequencies. Communicative cost, however, can be…
Numerous analyses of reading time (RT) data have been undertaken in the effort to learn more about the internal processes that occur during reading comprehension. However, data measured on words at the end of a sentence–or even clause–is often omitted due to the confounding factors introduced by so-…
When generating natural language from neural probabilistic models, high probability does not always coincide with high quality: It has often been observed that mode-seeking decoding methods, i.e., those that produce high-probability text under the model, lead to unnatural language. On the other hand…
A central quest of probing is to uncover how pre-trained models encode a linguistic property within their representations. An encoding, however, might be spurious—i.e., the model might not rely on it when making predictions. In this paper, we try to find an encoding that the model actually uses, int…
In this paper, we seek to measure how much information a component in a neural network could extract from the representations fed into it. Our work stands in contrast to prior probing work, most of which investigates how much information a model's representations contain. This shift in perspective l…
Pimentel et al. (2020) recently analysed probing from an information-theoretic perspective. They argue that probing should be seen as approximating a mutual information. This led to the rather unintuitive conclusion that representations encode exactly the same information about a target task as the…
Probes are models devised to investigate the encoding of knowledge—e.g. syntactic structure—in contextual representations. Probes are often designed for simplicity, which has led to restrictions on probe design that may not allow for the full exploitation of the structure of encoded information; one…
While there exist scores of natural languages, each with its unique features and idiosyncrasies, they all share a unifying theme: enabling human communication. We may thus reasonably predict that human cognition shapes how these languages evolve and are used. Assuming that the capacity to process in…
This work presents an information-theoretic operationalisation of cross-linguistic non-arbitrariness. It is not a new idea that there are small, cross-linguistic associations between the forms and meanings of words. For instance, it has been claimed (Blasi et al., 2016) that the word for “tongue” is…
The mapping of lexical meanings to wordforms is a major feature of natural languages. While usage pressures might assign short words to frequent meanings (Zipf’s law of abbreviation), the need for a productive and open-ended vocabulary, local constraints on sequences of symbols, and various other fa…
Homophony’s widespread presence in natural languages is a controversial topic. Recent theories of language optimality have tried to justify its prevalence, despite its negative effects on cognitive processing time, e.g., Piantadosi et al. (2012) argued homophony enables the reuse of efficient wordfo…
The uniform information density (UID) hypothesis posits a preference among language users for utterances structured such that information is distributed uniformly across a signal. While its implications on language production have been well explored, the hypothesis potentially makes predictions abou…
In common law, the outcome of a new case is determined mostly by precedent cases, rather than by existing statutes. However, how exactly does the precedent influence the outcome of a new case? Answering this question is crucial for guaranteeing fair and consistent judicial decision-making. We are th…
Representation learning is one of the foundations of Deep Learning and allowed important improvements on several Machine Learning tasks, such as Neural Machine Translation, Question Answering and Speech Recognition. Recent works have proposed new methods for learning representations for nodes and ed…