Related papers: Fine-grained Language Composition: A Case Study

Integrating pretrained vision-language foundation models like CLIP into federated learning has attracted significant attention for enhancing generalization across diverse tasks. Typically, federated learning of vision-language models…

Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) sometimes generate plausible-looking but functionally…

Training machine learning models requires feeding input data for models to ingest. Input pipelines for machine learning jobs are often challenging to implement efficiently as they require reading large volumes of data, applying complex…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components…

Instruction fine-tuning has recently emerged as a promising approach for improving the zero-shot capabilities of Large Language Models (LLMs) on new tasks. This technique has shown particular strength in improving the performance of…

Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of given design concepts, functional coherence--the integration…

Modern enterprise computing systems integrate numerous subsystems to resolve a common task by yielding emergent behavior. A widespread approach is using services implemented with Web technologies like REST or OpenAPI, which offer an…

Syntactically controlled paraphrase generation requires language models to generate paraphrases for sentences according to specific syntactic structures. Existing fine-tuning methods for this task are costly as all the parameters of the…

Natural language allows us to refer to novel composite concepts by combining expressions denoting their parts according to systematic rules, a property known as \emph{compositionality}. In this paper, we study whether the language emerging…

We analyse preference inference, through consistency, for general preference languages based on lexicographic models. We identify a property, which we call strong compositionality, that applies for many natural kinds of preference…

Despite the widely reported success of embedding-based machine learning methods on natural language processing tasks, the use of more easily interpreted engineered features remains common in fields such as cognitive impairment (CI)…

\emph{Literate programming}, introduced by Knurth, interleaves code and prose so that a program can be read as both executable and explanatory text. We propose \emph{literate execution}, which inverts this relationship: rather than…

In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This…

Bounded linear types have proved to be useful for automated resource analysis and control in functional programming languages. In this paper we introduce an affine bounded linear typing discipline on a general notion of resource which can…

Program synthesis techniques construct or infer programs from user-provided specifications, such as input-output examples. Yet most specifications, especially those given by end-users, leave the synthesis problem radically ill-posed,…

Pythonic idioms are highly valued and widely used in the Python programming community. However, many Python users find it challenging to use Pythonic idioms. Adopting a rule-based approach or LLM-only approach is not sufficient to overcome…

Pre-trained Language Models (PLMs) have demonstrated impressive performance in various NLP tasks. However, traditional fine-tuning methods for leveraging PLMs for downstream tasks entail significant computational overhead. Prompt-tuning has…

The problem of synthesis of gate-level descriptions of digital circuits from behavioural specifications written in higher-level programming languages (hardware compilation) has been studied for a long time yet a definitive solution has not…

Conventional federated learning (FL) assumes a closed world with a fixed total number of clients. In contrast, new clients continuously join the FL process in real-world scenarios, introducing new knowledge. This raises two critical…