相关论文: IRepair: An Intent-Aware Approach to Repair Data-D…

Structured pruning of large language models (LLMs) offers substantial efficiency improvements by removing entire hidden units, yet current approaches often suffer from significant performance degradation, particularly in zero-shot settings,…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Automated Program Repair (APR) attempts to patch software bugs and reduce manual debugging efforts. Very recently, with the advances in Large Language Models (LLMs), an increasing number of APR techniques have been proposed, facilitating…

The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians, and it is typically written by radiologists based on the 'Findings' section. However, writing numerous…

Large Language Models (LLMs) are effective for data augmentation in classification tasks like intent detection. In some cases, they inadvertently produce examples that are ambiguous with regard to untargeted classes. We present DDAIR…

Recent research has demonstrated the feasibility of training efficient intent detectors based on pre-trained language model~(PLM) with limited labeled data. However, deploying these detectors in resource-constrained environments such as…

Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated considerable potential in automated code repair, their…

The recent advancements in large language models (LLMs) have significantly improved language understanding and generation capabilities. However, it is difficult to deploy LLMs on resource-constrained edge devices due to their high…

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a significant increase in the harmfulness of LLM outputs. Building on…

Recent work has shown that directly fine-tuning large language models (LLMs) for dense retrieval yields strong performance, but their substantial parameter counts make them computationally inefficient. While prior studies have revealed…

Automated Program Repair (APR) aims to fix bugs by generating patches. And existing work has demonstrated that "pre-training and fine-tuning" paradigm enables Large Language Models (LLMs) improve fixing capabilities on APR. However,…

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language downstream tasks, a common practice is to employ task-specific…

Sequence-to-sequence models have been used to transform erroneous programs into correct ones when trained with a large enough dataset. Some recent studies also demonstrated strong empirical evidence that code review could improve the…

With the rapid development of cloud computing systems and the increasing complexity of their infrastructure, intelligent mechanisms to detect and mitigate failures in real time are becoming increasingly important. Traditional methods of…

Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity…