Black Big Boxes: Do Language Models Hide a Theory of Adjective Order?
- URL: http://arxiv.org/abs/2407.02136v1
- Date: Tue, 2 Jul 2024 10:29:09 GMT
- Title: Black Big Boxes: Do Language Models Hide a Theory of Adjective Order?
- Authors: Jaap Jumelet, Lisa Bylinina, Willem Zuidema, Jakub Szymanik,
- Abstract summary: In English and other languages, multiple adjectives in a complex noun phrase show intricate ordering patterns that have been a target of much linguistic theory.
We review existing hypotheses designed to explain Adjective Order Preferences (AOPs) in humans and develop a setup to study AOPs in language models.
We find that all models' predictions are much closer to human AOPs than predictions generated by factors identified in theoretical linguistics.
- Score: 5.395055685742631
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In English and other languages, multiple adjectives in a complex noun phrase show intricate ordering patterns that have been a target of much linguistic theory. These patterns offer an opportunity to assess the ability of language models (LMs) to learn subtle rules of language involving factors that cross the traditional divisions of syntax, semantics, and pragmatics. We review existing hypotheses designed to explain Adjective Order Preferences (AOPs) in humans and develop a setup to study AOPs in LMs: we present a reusable corpus of adjective pairs and define AOP measures for LMs. With these tools, we study a series of LMs across intermediate checkpoints during training. We find that all models' predictions are much closer to human AOPs than predictions generated by factors identified in theoretical linguistics. At the same time, we demonstrate that the observed AOPs in LMs are strongly correlated with the frequency of the adjective pairs in the training data and report limited generalization to unseen combinations. This highlights the difficulty in establishing the link between LM performance and linguistic theory. We therefore conclude with a road map for future studies our results set the stage for, and a discussion of key questions about the nature of knowledge in LMs and their ability to generalize beyond the training sets.
Related papers
- Can Language Models Learn Typologically Implausible Languages? [62.823015163987996]
Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans.
We discuss how language models (LMs) allow us to better determine the role of domain-general learning biases in language universals.
We test LMs on an array of highly naturalistic but counterfactual versions of the English (head-initial) and Japanese (head-final) languages.
arXiv Detail & Related papers (2025-02-17T20:40:01Z) - Large Language Models as Proxies for Theories of Human Linguistic Cognition [2.624902795082451]
We consider the possible role of current large language models (LLMs) in the study of human linguistic cognition.
We focus on the use of such models as proxies for theories of cognition that are relatively linguistically-neutral in their representations and learning.
arXiv Detail & Related papers (2025-02-11T16:38:16Z) - Randomly Sampled Language Reasoning Problems Reveal Limits of LLMs [8.146860674148044]
We attempt to measure models' language understanding capacity while circumventing the risk of dataset recall.
We parameterize large families of language tasks recognized by deterministic finite automata (DFAs)
We find that, even in the strikingly simple setting of 3-state DFAs, LLMs underperform un parameterized ngram models on both language recognition and synthesis tasks.
arXiv Detail & Related papers (2025-01-06T07:57:51Z) - From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition [6.617999710257379]
We propose a three-stage framework to assess the abilities of LMs.
We evaluate the generative capacities of LMs using methods from linguistic research.
arXiv Detail & Related papers (2024-10-17T06:31:49Z) - What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages [78.1866280652834]
Large language models (LM) are distributions over strings.
We investigate the learnability of regular LMs (RLMs) by RNN and Transformer LMs.
We find that the complexity of the RLM rank is strong and significant predictors of learnability for both RNNs and Transformers.
arXiv Detail & Related papers (2024-06-06T17:34:24Z) - Holmes: A Benchmark to Assess the Linguistic Competence of Language Models [59.627729608055006]
We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence.
We use computation-based probing to examine LMs' internal representations regarding distinct linguistic phenomena.
As a result, we meet recent calls to disentangle LMs' linguistic competence from other cognitive abilities.
arXiv Detail & Related papers (2024-04-29T17:58:36Z) - Explanation-aware Soft Ensemble Empowers Large Language Model In-context
Learning [50.00090601424348]
Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks.
We propose EASE, an Explanation-Aware Soft Ensemble framework to empower in-context learning with LLMs.
arXiv Detail & Related papers (2023-11-13T06:13:38Z) - How Abstract Is Linguistic Generalization in Large Language Models?
Experiments with Argument Structure [2.530495315660486]
We investigate the degree to which pre-trained Transformer-based large language models represent relationships between contexts.
We find that LLMs perform well in generalizing the distribution of a novel noun argument between related contexts.
However, LLMs fail at generalizations between related contexts that have not been observed during pre-training.
arXiv Detail & Related papers (2023-11-08T18:58:43Z) - Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
We evaluate language understanding capacities on simple inference tasks that most humans find trivial.
We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments.
The models exhibit moderate to low performance on these evaluation sets.
arXiv Detail & Related papers (2023-05-24T06:41:09Z) - Shortcut Learning of Large Language Models in Natural Language
Understanding [119.45683008451698]
Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks.
They might rely on dataset bias and artifacts as shortcuts for prediction.
This has significantly affected their generalizability and adversarial robustness.
arXiv Detail & Related papers (2022-08-25T03:51:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.