Large Language Models (LLMs) have been widely employed in programming language analysis to enhance human productivity. Yet, their reliability can be compromised by various code distribution shifts, leading to inconsistent outputs. While probabilistic methods are known to mitigate such impact through uncertainty calibration and estimation, their efficacy in the language domain remains underexplored compared to their application in image-based tasks. In this work, we first introduce a large-scale benchmark dataset, incorporating three realistic patterns of code distribution shifts at varying intensities. Then we thoroughly investigate state-of-the-art probabilistic methods applied to CodeLlama using these shifted code snippets. We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision. However, our study further reveals varied performance dynamics across different criteria (e.g., calibration error vs misclassification detection) and trade-off between efficacy and efficiency, highlighting necessary methodological selection tailored to specific contexts.

Joint entity and relation extraction is a process that identifies entity pairs and their relations using a single model. We focus on the problem of training these models on distantly-labeled data, which is generated by aligning entity mentions in a text corpus with their corresponding entity and relation types in a knowledge base. One key challenge here is the presence of noisy labels, which arises from both entity and relation annotations, and significantly impair the effectiveness of supervised learning applications. However, existing research primarily addresses only one type of noise, thereby limiting the effectiveness of noise reduction. To fill this gap, we introduce a new noise-robust approach, that 1)~incorporates a pre-trained GPT-2 into a sequence tagging scheme for simultaneous entity and relation detection, and 2)~employs a noise-robust learning framework which includes a new loss function that penalizes inconsistency with both significant relation patterns and entity-relation dependencies, as well as a self-adaptive learning step that iteratively selects and trains on high-quality instances. Experiments on two datasets show that our method outperforms the existing state-of-the-art methods in both joint extraction performance and noise reduction effect.