Related papers: Learning Code-Edit Embedding to Model Student Debu…
As online education platforms continue to expand, there is a growing need for assessment methods that not only measure answer accuracy but also capture the depth of students' cognitive processes in alignment with curriculum objectives. This…
Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale…
Embedding models have demonstrated strong performance in tasks like clustering, retrieval, and feature extraction while offering computational advantages over generative models and cross-encoders. Benchmarks such as MTEB have shown that…
Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs'…
Code generation aims to automatically generate a piece of code given an input natural language utterance. Currently, among dominant models, it is treated as a sequence-to-tree task, where a decoder outputs a sequence of actions…
Programming problems can be solved in a multitude of functionally correct ways, but the quality of these solutions (e.g. readability, maintainability) can vary immensely. When code quality is poor, symptoms emerge in the form of 'code…
Large Language Models (LLMs) can generate plausible test code. Intuitively they generate this by imitating tests seen in their training data, rather than reasoning about execution semantics. However, such reasoning is important when…
Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundational coding knowledge on large, general-purpose datasets…
Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only concatenates the answered examples as demonstrations to the…
We propose a novel word embedding pre-training approach that exploits writing errors in learners' scripts. We compare our method to previous models that tune the embeddings based on script scores and the discrimination between correct and…
Modeling long histories plays a pivotal role in enhancing recommendation systems, allowing to capture user's evolving preferences, resulting in more precise and personalized recommendations. In this study we tackle the challenges of…
The problem of optimal actuation for channel and source coding was recently formulated and solved in a number of relevant scenarios. In this class of models, actions are taken at encoders or decoders, either to acquire side information in…
Source code processing heavily relies on the methods widely used in natural language processing (NLP), but involves specifics that need to be taken into account to achieve higher quality. An example of this specificity is that the semantics…
Decoding brain imaging data are gaining popularity, with applications in brain-computer interfaces and the study of neural representations. Decoding is typicallysubject-specific and does not generalise well over subjects, due to high…
While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime…
Reading, understanding and explaining code have traditionally been important skills for novices learning programming. As large language models (LLMs) become prevalent, these foundational skills are more important than ever given the…
Large language models (LLMs) with decoder-only architectures demonstrate remarkable in-context learning (ICL) capabilities. This feature enables them to effectively handle both familiar and novel tasks by utilizing examples provided within…
Large Language Models trained on code corpora (code-LLMs) have demonstrated impressive performance in various coding assistance tasks. However, despite their increased size and training dataset, code-LLMs still have limitations such as…
Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's own history, overlooking inter-user differences that are…
Common knowledge distillation methods require the teacher model and the student model to be trained on the same task. However, the usage of embeddings as teachers has also been proposed for different source tasks and target tasks. Prior…