Related papers: How Code Representation Shapes False-Positive Dyna…

Large Language Models (LLMs) have shown promising performance in software vulnerability detection, particularly after domain-specific Supervised Fine-Tuning (SFT). However, it remains unclear whether these models genuinely internalize…

Generating accurate code review comments remains a significant challenge due to the inherently diverse and non-unique nature of the task output. Large language models pretrained on both programming and natural language data tend to perform…

Fine-tuning speech representation models can enhance performance on specific tasks but often compromises their cross-task generalization ability. This degradation is often caused by excessive changes in the representations, making it…

Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease the subsequent acquisition of rich semantic knowledge, much…

Large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, particularly in automated program repair. However, the effectiveness of such repairs is highly dependent on the performance of upstream fault…

With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing…

With the recent advancement of Large Language Models (LLMs), generating functionally correct code has become less complicated for a wide array of developers. While using LLMs has sped up the functional development process, it poses a heavy…

We study model merging as a practical alternative to conventional adaptation strategies for code-mixed NLP. Starting from a multilingual base model, we: (i) perform continued pre-training (CPT) on unlabeled code-mixed text to obtain an…

LLM deployment in critical domains is currently impeded by persistent hallucinations--generating plausible but factually incorrect assertions. While scaling laws drove significant improvements in general capabilities, theoretical frameworks…

Do multilingual embedding models encode a language-general representation of proficiency? We investigate this by training linear and non-linear probes on hidden-state activations from Qwen3-Embedding (0.6B, 4B, 8B) to predict CEFR…

An effective and efficient encoding of the source code of a computer program is critical to the success of sequence-to-sequence deep neural network models for tasks in computer program comprehension, such as automated code summarization and…

While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear. In this paper, we conduct a detailed diagnostic analysis…

This study examines whether Low-Rank Adaptation (LoRA) fine-tuned Large Language Models (LLMs) can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware…

Assertion messages significantly enhance unit tests by clearly explaining the reasons behind test failures, yet they are frequently omitted by developers and automated test-generation tools. Despite recent advancements, Large Language…

Finetuning large language models (LLMs) has been empirically effective on a variety of downstream tasks. Existing approaches to finetuning an LLM either focus on parameter-efficient finetuning, which only updates a small number of trainable…

Multilingual programming, which involves using multiple programming languages (PLs) in a single project, is increasingly common due to its benefits. However, it introduces cross-language bugs (CLBs), which arise from interactions between…

Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language steering, a lightweight inference-time method that…