Related papers: Towards Human-interpretable Explanation in Code Cl…
Large Language Models (LLMs), exemplified by ChatGPT, have significantly reshaped text generation, particularly in the realm of writing assistance. While ethical considerations underscore the importance of transparently acknowledging LLM…
Large language models (LLMs) have demonstrated significant potential in the realm of natural language understanding and programming code processing tasks. Their capacity to comprehend and generate human-like code has spurred research into…
While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if…
Binary code analysis plays a pivotal role in the field of software security and is widely used in tasks such as software maintenance, malware detection, software vulnerability discovery, patch analysis, etc. However, unlike source code,…
Language models (LMs) like GPT-4 are important in AI applications, but their opaque decision-making process reduces user trust, especially in safety-critical areas. We introduce LMExplainer, a novel knowledge-grounded explainer that…
To ensure safe driving in dynamic environments, autonomous vehicles should possess the capability to accurately predict lane change intentions of surrounding vehicles in advance and forecast their future trajectories. Existing motion…
Large Language Models (LLMs) recently demonstrated capabilities for generating source code in common programming languages. Additionally, commercial products such as ChatGPT 4 started to provide code interpreters, allowing for the automatic…
Recommendation Systems have become integral to modern user experiences, but lack transparency in their decision-making processes. Existing explainable recommendation methods are hindered by reliance on a post-hoc paradigm, wherein…
In cyberattack detection and prevention systems, cybersecurity analysts always prefer solutions that are as interpretable and understandable as rule-based or signature-based detection. This is because of the need to tune and optimize these…
Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by…
Detecting code clones is relevant to software maintenance and code refactoring. This challenge still presents unresolved cases, mainly when structural similarity does not reflect functional equivalence, though recent code models show…
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…
Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static semantics inference, and dynamic reasoning. Traditional tools are…
Large Language Models (LLMs) are increasingly used to generate textual explanations of process models discovered from event logs. Producing explanations from large behavioral abstractions (e.g., directly-follows graphs or Petri nets) can be…
Large Language Models (LLMs) offer new potential for automating documentation-to-code traceability, yet their capabilities remain underexplored. We present a comprehensive evaluation of LLMs (Claude 3.5 Sonnet, GPT-4o, and o3-mini) in…
Recent research has explored the creation of questions from code submitted by students. These Questions about Learners' Code (QLCs) are created through program analysis, exploring execution paths, and then creating code comprehension…
Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black-box large language models. They often achieve strong correlations with human…
Vulnerability detectors based on deep learning (DL) models have proven their effectiveness in recent years. However, the shroud of opacity surrounding the decision-making process of these detectors makes it difficult for security analysts…
Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…
As Machine Learning (ML) models grow in size and demand higher-quality training data, the expenses associated with re-training and fine-tuning these models are escalating rapidly. Inspired by recent impressive achievements of Large Language…