Construction Grammar hypothesizes that knowledge of a language consists chiefly of knowledge of form-meaning pairs (''constructions'') that include vocabulary, general grammar rules, and even idiosyncratic patterns. Recent work has shown that transformer language models represent at least some constructional patterns, including ones where the construction is rare overall. In this work, we probe BERT's representation of the form and meaning of a minor construction of English, the NPN (noun-preposition-noun) construction -- exhibited in such expressions as face to face and day to day -- which is known to be polysemous. We construct a benchmark dataset of semantically annotated corpus instances (including distractors that superficially resemble the construction). With this dataset, we train and evaluate probing classifiers. They achieve decent discrimination of the construction from distractors, as well as sense disambiguation among true instances of the construction, revealing that BERT embeddings carry indications of the construction's semantics. Moreover, artificially permuting the word order of true construction instances causes them to be rejected, indicating sensitivity to matters of form. We conclude that BERT does latently encode at least some knowledge of the NPN construction going beyond a surface syntactic pattern and lexical cues.

Electronic Health Records (EHRs) offer rich potential for clinical prediction, yet their inherent complexity and heterogeneity pose significant challenges for traditional machine learning approaches. Domain-specific EHR foundation models trained on large collections of unlabeled EHR data have demonstrated promising improvements in predictive accuracy and generalization; however, their training is constrained by limited access to diverse, high-quality datasets and inconsistencies in coding standards and healthcare practices. In this study, we explore the possibility of using general-purpose Large Language Models (LLMs) based embedding methods as EHR encoders. By serializing patient records into structured Markdown text, transforming codes into human-readable descriptors, we leverage the extensive generalization capabilities of LLMs pretrained on vast public corpora, thereby bypassing the need for proprietary medical datasets. We systematically evaluate two state-of-the-art LLM-embedding models, GTE-Qwen2-7B-Instruct and LLM2Vec-Llama3.1-8B-Instruct, across 15 diverse clinical prediction tasks from the EHRSHOT benchmark, comparing their performance to an EHRspecific foundation model, CLIMBR-T-Base, and traditional machine learning baselines. Our results demonstrate that LLM-based embeddings frequently match or exceed the performance of specialized models, even in few-shot settings, and that their effectiveness scales with the size of the underlying LLM and the available context window. Overall, our findings demonstrate that repurposing LLMs for EHR encoding offers a scalable and effective approach for clinical prediction, capable of overcoming the limitations of traditional EHR modeling and facilitating more interoperable and generalizable healthcare applications.

The claim matching (CM) task can benefit an automated fact-checking pipeline by putting together claims that can be resolved with the same fact-check. In this work, we are the first to explore zero-shot and few-shot learning approaches to the task. We consider CM as a binary classification task and experiment with a set of instruction-following large language models (GPT-3.5-turbo, Gemini-1.5-flash, Mistral-7B-Instruct, and Llama-3-8B-Instruct), investigating prompt templates. We introduce a new CM dataset, ClaimMatch, which will be released upon acceptance. We put LLMs to the test in the CM task and find that it can be tackled by leveraging more mature yet similar tasks such as natural language inference or paraphrase detection. We also propose a pipeline for CM, which we evaluate on texts of different lengths.

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context Learning (ICL) adapts the model to a new task by simply including examples in the input without any training. When applying optimization-based methods, such as fine-tuning and PT for few-shot learning, the model is specifically adapted to the small set of training examples, whereas ICL leaves the model unchanged. This distinction makes traditional learning methods more prone to overfitting; in contrast, ICL is less sensitive to the few-shot scenario. While ICL is not prone to overfitting, it does not fully extract the information that exists in the training examples. This work introduces Context-aware Prompt Tuning (CPT), a method inspired by ICL, PT, and adversarial attacks. We build on the ICL strategy of concatenating examples before the input, but we extend this by PT-like learning, refining the context embedding through iterative optimization to extract deeper insights from the training examples. We carefully modify specific context tokens, considering the unique structure of input and output formats. Inspired by adversarial attacks, we adjust the input based on the labels present in the context, focusing on minimizing, rather than maximizing, the loss. Moreover, we apply a projected gradient descent algorithm to keep token embeddings close to their original values, under the assumption that the user-provided data is inherently valuable. Our method has been shown to achieve superior accuracy across multiple classification tasks using various LLM models.

The Abstraction and Reasoning Corpus (ARC) was recently introduced by Fran\c{c}ois Chollet as a tool to measure broad intelligence in both humans and machines. It is very challenging, and the best approach in a Kaggle competition could only solve 20% of the tasks, relying on brute-force search for chains of hand-crafted transformations. In this paper, we present the first steps exploring an approach based on descriptive grid models and the Minimum Description Length (MDL) principle. The grid models describe the contents of a grid, and support both parsing grids and generating grids. The MDL principle is used to guide the search for good models, i.e. models that compress the grids the most. We report on our progress over a year, improving on the general approach and the models. Out of the 400 training tasks, our performance increased from 5 to 29 solved tasks, only using 30s computation time per task. Our approach not only predicts the output grids, but also outputs an intelligible model and explanations for how the model was incrementally built.