More Like this

1. Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

   Zhu, Zhaowei; Wang, Jialu; Cheng, Hao; Liu, Yang (May 2024, International Conference on Learning Representations)

   Language models have shown promise in various tasks but can be affected by undesired data during training, fine-tuning, or alignment. For example, if some unsafe conversations are wrongly annotated as safe ones, the model fine-tuned on these samples may be harmful. Therefore, the correctness of annotations, i.e., the credibility of the dataset, is important. This study focuses on the credibility of real-world datasets, including the popular benchmarks Jigsaw Civil Comments, Anthropic Harmless & Red Team, PKU BeaverTails & SafeRLHF, that can be used for training a harmless language model. Given the cost and difficulty of cleaning these datasets by humans, we introduce a systematic framework for evaluating the credibility of datasets, identifying label errors, and evaluating the influence of noisy labels in the curated language data, specifically focusing on unsafe comments and conversation classification. With the framework, we find and fix an average of 6.16% label errors in 11 datasets constructed from the above benchmarks. The data credibility and downstream learning performance can be remarkably improved by directly fixing label errors, indicating the significance of cleaning existing real-world datasets. 

   more » « less
2. Revisiting Pre-trained Language Models for Vulnerability Detection

   https://doi.org/10.1145/3779208.3785291  

   Li, Youpeng; Qi, Weiliang; Wang, Xuyu; Yu, Fuxun; Wang, Xinda (June 2026, ACM)

   The rapid advancement of pre-trained language models (PLMs) has demonstrated promising results for various code-related tasks. However, their effectiveness in detecting real-world vulnerabilities remains a critical challenge. While existing empirical studies evaluate PLMs for vulnerability detection (VD), they suffer from data leakage, limited scope, and superficial analysis, hindering the accuracy and comprehensiveness of evaluations. This paper begins by revisiting the common issues in existing research on PLMs for VD through the evaluation pipeline. It then proceeds with an accurate and extensive evaluation of 18 PLMs, spanning model parameters from millions to billions, on high-quality datasets that feature accurate labeling, diverse vulnerability types, and various projects. Specifically, we compare the performance of PLMs under both fine-tuning and prompt engineering, assess their effectiveness and generalizability across various training and testing settings, and analyze their robustness to perturbations such as code normalization, abstraction, and semantic-preserving transformations. Our findings reveal that, for function-level VD, PLMs incorporating pre-training tasks designed to capture the syntactic and semantic patterns of code outperform both general-purpose PLMs and those solely pre-trained or fine-tuned on large code corpora. However, these models face notable challenges in real-world scenarios, such as difficulties in detecting vulnerabilities with complex dependencies, handling perturbations introduced by code normalization and abstraction, and identifying semantic-preserving vulnerable code transformations. Also, the truncation caused by the limited context windows of PLMs can lead to a non-negligible number of labeling errors, which is overlooked by previous work. This study underscores the importance of thorough evaluations of model performance in practical scenarios and outlines future directions to help enhance the effectiveness of PLMs for realistic VD applications. 

   more » « less
3. MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

   Sprague, Zayne; Ye, Xi; Bostrom, Kaj; Chaudhuri, Swarat; Durrett, Greg (May 2024, Proceedings of the International Conference on Learning Representations)

   While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in complex settings. However, evaluating LLM reasoning is challenging because system capabilities continue to grow while benchmark datasets for tasks like logical deduction have remained static. We introduce MuSR, a dataset for evaluating language models on multistep soft reasoning tasks specified in a natural language narrative. This dataset has two crucial features. First, it is created through a novel neurosymbolic synthetic-to-natural generation algorithm, enabling the construction of complex reasoning instances that challenge GPT-4 (e.g., murder mysteries roughly 1000 words in length) and which can be scaled further as more capable LLMs are released. Second, our dataset instances are free text narratives corresponding to real-world domains of reasoning; this makes it simultaneously much more challenging than other synthetically-crafted benchmarks while remaining realistic and tractable for human annotators to solve with high accuracy. We evaluate a range of LLMs and prompting techniques on this dataset and characterize the gaps that remain for techniques like chain-of-thought to perform robust reasoning. 

   more » « less
4. CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning

   Roy, MK; Chen, S; Steenhoek, B; Peng, J; Kaiser, G; Ray, B; Le, W (January 2026, The Fourteenth International Conference on Learning Representations (ICLR))

   Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or educational coding problems and focus on coarse-grained reasoning tasks such as input/output prediction, limiting their effectiveness in evaluating LLMs in practical SE contexts. To bridge this gap, we propose CodeSense, the first benchmark that makes available a spectrum of fine-grained code reasoning tasks concerned with the software engineering of real-world code. We collected Python, C and Java software projects from real-world repositories. We executed tests from these repositories, collected their execution traces, and constructed a ground truth dataset for fine-grained semantic reasoning tasks. We then performed comprehensive evaluations on state-of-the-art LLMs. Our results show a clear performance gap for the models to handle fine-grained reasoning tasks. Although prompting techniques such as chain-of-thought and in-context learning helped, the lack of code semantics in LLMs fundamentally limit models' capabilities of code reasoning. Besides dataset, benchmark and evaluation, our work produced an execution tracing framework and tool set that make it easy to collect ground truth for fine-grained SE reasoning tasks, offering a strong basis for future benchmark construction and model post training. Our code and data are located at \url{https://codesense-bench.github.io/}. 

   more » « less
5. Efficient Adaptation of Large Language Models for Smart Contract Vulnerability Detection

   https://doi.org/10.1145/3727582.3728688  

   Sikder, Fadul; Lei, Yu; Ji, Yuede (June 2025, ACM)

   Smart contracts underpin decentralized applications but face significant security risks from vulnerabilities, while traditional analysis methods have limitations. Large Language Models (LLMs) offer promise for vulnerability detection, yet adapting these powerful models efficiently, particularly generative ones, remains challenging. This paper investigates two key strategies for the efficient adaptation of LLMs for Solidity smart contract vulnerability detection: (1) replacing token-level generation with a dedicated classification head during fine-tuning, and (2) selectively freezing lower transformer layers using Low-Rank Adaptation (LoRA). Our empirical evaluation demonstrates that the classification head approach enables models like Llama 3.2 3B to achieve high accuracy (77.5%), rivaling the performance of significantly larger models such as the fine-tuned GPT-3.5. Furthermore, we show that selectively freezing bottom layers reduces training time and memory usage by approximately 10-20% with minimal impact on accuracy. Notably, larger models (3B vs. 1B parameters) exhibit greater resilience to layer freezing, maintaining high accuracy even with a large proportion of layers frozen, suggesting a localization of general code understanding in lower layers versus task-specific vulnerability patterns in upper layers. These findings present practical insights for developing and deploying performant LLM-based vulnerability detection systems efficiently, particularly in resource-constrained settings. 

   more » « less