Related papers: The Curious Case of Control

Deployed language and vision-language models must decide, on each input, whether to answer directly, retrieve evidence, defer to a stronger model, or abstain. Contrary to the common monotonicity intuition, greater per-input expressivity is…

People exhibit a tendency to generalize a novel noun to the basic-level in a hierarchical taxonomy -- a cognitively salient category such as "dog" -- with the degree of generalization depending on the number and type of exemplars. Recently,…

A range of studies have concluded that neural word prediction models can distinguish grammatical from ungrammatical sentences with high accuracy. However, these studies are based primarily on monolingual evidence from English. To…

Grammatical rules in natural languages are often characterized by exceptions. How do language learners learn these exceptions to otherwise general patterns? Here, we study this question through the case study of English passivization. While…

We present a model for pragmatically describing scenes, in which contrastive behavior results from a combination of inference-driven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a…

LSTMs trained on next-word prediction can accurately perform linguistic tasks that require tracking long-distance syntactic dependencies. Notably, model accuracy approaches human performance on number agreement tasks (Gulordava et al.,…

Large language models are powerful systems that excel at many tasks, ranging from translation to mathematical reasoning. Yet, at the same time, these models often show unhuman-like characteristics. In the present paper, we address this gap…

The finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the input by itself. However, there does not exist a mechanism…

Recent zero-shot evaluations have highlighted important limitations in the abilities of language models (LMs) to perform meaning extraction. However, it is now well known that LMs can demonstrate radical improvements in the presence of…

Many organizations require their customer-care agents to manually summarize their conversations with customers. These summaries are vital for decision making purposes of the organizations. The perspective of the summary that is required to…

Previous work has shown correlations between the hidden states of large language models and fMRI brain responses, on language tasks. These correlations have been taken as evidence of the representational similarity of these models and brain…

Hierarchical model fitting has become commonplace for case-control studies of cognition and behaviour in mental health. However, these techniques require us to formalise assumptions about the data-generating process at the group level,…

Neural text generation (data- or text-to-text) demonstrates remarkable performance when training data is abundant which for many applications is not the case. To collect a large corpus of parallel data, heuristic rules are often used but…

Conversational agents have become an integral part of the general population for simple task enabling situations. However, these systems are yet to have any social impact on the diverse and minority population, for example, helping people…

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the…

We propose a model of inference and heuristic decision-making in groups that is rooted in the Bayes rule but avoids the complexities of rational inference in partially observed environments with incomplete information, which are…

Intelligent agents, such as robots, are increasingly deployed in real-world, human-centric environments. To foster appropriate human trust and meet legal and ethical standards, these agents must be able to explain their behavior. However,…

Large Language Models (LLMs) excel at text summarization, a task that requires models to select content based on its importance. However, the exact notion of salience that LLMs have internalized remains unclear. To bridge this gap, we…

How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs' syntactic performance (e.g., on…

We examine whether large neural language models, trained on very large collections of varied English text, learn the potentially long-distance dependency of British versus American spelling conventions, i.e., whether spelling is…