English
Related papers

Related papers: DISTINCT: A Description-Guided Branch-Consistency …

200 papers

Discrete diffusion models are a powerful, emerging paradigm for code generation. They construct programs through iterative refinement of partially corrupted token sequences and enable parallel token refinement. Importantly, this paradigm…

Computation and Language · Computer Science 2026-05-19 Lize Shao , Michael Cardei , Zichen Xie , Ferdinando Fioretto , Wenxi Wang

There has been a growing interest in using Large Language Models (LLMs) for code review thanks to their proven proficiency in code comprehension. The primary objective of most review scenarios is to generate desired review comments (DRCs)…

Software Engineering · Computer Science 2025-01-07 Yongda Yu , Lei Zhang , Guoping Rong , Haifeng Shen , Jiahao Zhang , Haoxiang Yan , Guohao Shi , Dong Shao , Ruiqi Pan , Yuan Li , Qiushi Wang , Zhao Tian

Today, most automated test generators, such as search-based software testing (SBST) techniques focus on achieving high code coverage. However, high code coverage is not sufficient to maximise the number of bugs found, especially when given…

Software Engineering · Computer Science 2021-09-28 Anjana Perera , Aldeida Aleti , Marcel Böhme , Burak Turhan

The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated…

Computation and Language · Computer Science 2024-12-18 Zhen Tao , Yanfang Chen , Dinghao Xi , Zhiyu Li , Wei Xu

While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipulable model of the world. As a consequence, current LMs also…

Computation and Language · Computer Science 2024-06-28 Afra Feyza Akyürek , Ekin Akyürek , Leshem Choshen , Derry Wijaya , Jacob Andreas

This study demonstrates that the modern generation of Large Language Models (LLMs, such as GPT-4) suffers from the same out-of-domain (OOD) performance gap observed in prior research on pre-trained Language Models (PLMs, such as BERT). We…

Computation and Language · Computer Science 2024-12-31 Dmitri Roussinov , Serge Sharoff , Nadezhda Puchnina

Writing good software tests can be challenging, therefore approaches that support developers are desirable. While generating complete tests automatically is such an approach commonly proposed in research, developers may already have…

Software Engineering · Computer Science 2025-04-30 Severin Primbs , Benedikt Fein , Gordon Fraser

Static analysis is effective for discovering software vulnerabilities but notoriously suffers from incomplete source--sink specifications and excessive false positives (FPs). We present \textsc{AdaTaint}, an LLM-driven taint analysis…

Software Engineering · Computer Science 2025-11-07 Shiyin Lin

Most research about natural language generation (NLG) relies on evaluation benchmarks with limited references for a sample, which may result in poor correlations with human judgements. The underlying reason is that one semantic meaning can…

Computation and Language · Computer Science 2024-05-28 Tianyi Tang , Hongyuan Lu , Yuchen Eleanor Jiang , Haoyang Huang , Dongdong Zhang , Wayne Xin Zhao , Tom Kocmi , Furu Wei

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

Computation and Language · Computer Science 2025-03-21 Ishika Agarwal , Krishnateja Killamsetty , Lucian Popa , Marina Danilevksy

Large language models (LLMs) show promise in automating clinical diagnosis, yet their non-transparent decision-making and limited alignment with diagnostic standards hinder trust and clinical adoption. We address this challenge by proposing…

Artificial Intelligence · Computer Science 2025-11-25 Yining Yuan , J. Ben Tamo , Micky C. Nnamdi , Yifei Wang , May D. Wang

The ubiquitous adoption of Large Language Generation Models (LLMs) in programming has underscored the importance of differentiating between human-written code and code generated by intelligent models. This paper specifically aims to…

Software Engineering · Computer Science 2023-07-06 Li Ke , Hong Sheng , Fu Cai , Zhang Yunhe , Liu Ming

Safety critical software assessment requires robust assessment against complex regulatory frameworks, a process traditionally limited by manual evaluation. This paper presents Document Retrieval-Augmented Fine-Tuning (DRAFT), a novel…

Large Language Models (LLMs), such as ChatGPT, are increasingly leveraged for generating both traditional software code and spreadsheet logic. Despite their impressive generative capabilities, these models frequently exhibit critical issues…

Software Engineering · Computer Science 2025-11-27 Simon Thorne , Advait Sarkar

Automatically detecting software failures is an important task and a longstanding challenge. It requires finding failure-inducing test cases whose test input can trigger the software's fault, and constructing an automated oracle to detect…

Software Engineering · Computer Science 2023-09-12 Tsz-On Li , Wenxi Zong , Yibo Wang , Haoye Tian , Ying Wang , Shing-Chi Cheung , Jeff Kramer

Fault localization (FL) is a critical but time-consuming task in software debugging, aiming to identify faulty code elements. While recent advances in large language models (LLMs) have shown promise for FL, they often struggle with complex…

Software Engineering · Computer Science 2025-09-26 Xinyu Shi , Zhenhao Li , An Ran Chen

Large language model (LLM)-based debugging systems can generate failure explanations, but these explanations may be incomplete or incorrect. Misleading explanations are harmful for downstream tasks (e.g., bug triage, bug fixing). We…

Software Engineering · Computer Science 2026-05-21 Julius Porbeck , Christian Medeiros Adriano , Holger Giese

Recent advances in image generation have led to the widespread availability of highly realistic synthetic media, increasing the difficulty of reliable deepfake detection. A key challenge is generalization, as detectors trained on a narrow…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Yichen Jiang , Mohammed Talha Alam , Sohail Ahmed Khan , Duc-Tien Dang-Nguyen , Fakhri Karray

Large language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g., ancestry-based disease incidence) or contextually justified (e.g., religious hiring…

Computation and Language · Computer Science 2026-04-21 Ziwen Pan , Zihan Liang , Jad Kabbara , Ali Emami

When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to…

Computation and Language · Computer Science 2025-10-21 Yiqi Li , Yusheng Liao , Zhe Chen , Yanfeng Wang , Yu Wang