Search Results - Computing methodologies Artificial intelligence Natural language processing

Code to Comment "Translation": Data, Metrics, Baselining & Evaluation by Gros, David, Sezhiyan, Hariharan, Devanbu, Prem, Yu, Zhou

“… More recently, researchers have applied deep-learning methods to this task-specifically, trainable generative translation models which are known to work very well for Natural Language translation (e.g…”
Get full text

AASD: Accelerate Inference by Aligning Speculative Decoding in Multimodal Large Language Models by Yang, Chaoqun, Chen, Ran, Zhang, Muyang, Pang, Weiguang, Chen, Yuzhi, Xu, Rongtao, Fu, Kexue, Wang, Changwei, Gao, Longxiang

“…Multimodal Large Language Models (MLLMs) have achieved notable success in visual instruction tuning, yet their inference is time-consuming due to the auto-regressive decoding of Large Language Model (LLM) backbone…”
Get full text

Unleashing the True Potential of Semantic-Based Log Parsing with Pre-Trained Language Models by Le, Van-Hoang, Xiao, Yi, Zhang, Hongyu

“… These log parsers fine-tune a small pre-trained language model (PLM) such as RoBERTa on a few labelled log samples…”
Get full text

Automatically Generating Content for Testing Autonomous Vehicles from User Descriptions by Steininger, Benedikt, Papamichail, Chrysanthi, Stark, David, Nickovic, Dejan, Gambi, Alessio

“… that generates focused scenarios by translating user requirements in natural language into three-dimensional road models…”
Get full text

Code Difference Guided Adversarial Example Generation for Deep Code Models by Tian, Zhao, Chen, Junjie, Jin, Zhi

“…Adversarial examples are important to test and enhance the robustness of deep code models. As source code is discrete and has to strictly stick to complex…”
Get full text

Log Parsing: How Far Can ChatGPT Go? by Le, Van-Hoang, Zhang, Hongyu

“… In recent studies, ChatGPT, the current cutting-edge large language model (LLM), has been widely applied to a wide range of software engineering tasks…”
Get full text

ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching by Zhao, Youpeng, Wu, Di, Wang, Jun

“…The Transformer architecture has significantly advanced natural language processing (NLP…”
Get full text

InfeRE: Step-by-Step Regex Generation via Chain of Inference by Zhang, Shuai, Gu, Xiaodong, Chen, Yuting, Shen, Beijun

“…Automatically generating regular expressions (abbrev. regexes) from natural language description (NL2RE…”
Get full text

Late Breaking Results: Fine-Tuning LLMs for Test Stimuli Generation by Park, Hyeonwoo, Park, Seonghyeon, Kang, Seokhyeong

“…The understanding and reasoning capabilities of large language models (LLMs) with text data have made them widely used for test stimuli generation…”
Get full text

Generating Variable Explanations via Zero-shot Prompt Learning by Wang, Chong, Lou, Yiling, Liu, Junwei, Peng, Xin

“… Therefore, in this paper, we target at generating concise natural language explanations for variables to facilitate program comprehension…”
Get full text

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding by Wei, Linye, Zhong, Shuzhang, Xu, Songqiang, Wang, Runsheng, Huang, Ru, Li, Meng

“…Large language model (LLM)-based automatic speech recognition (ASR) has recently attracted a lot of attention due to its high recognition accuracy and enhanced multi-dialect support…”
Get full text

Can Large Language Models Comprehend Code Stylometry? by Dipongkor, Atish Kumar

“… In this study, we initially fine-tune five Large Language Models (LLMs) for CAA and evaluate their performance…”
Get full text

LEAP: Efficient and Automated Test Method for NLP Software by Xiao, Mingxuan, Xiao, Yan, Dong, Hai, Ji, Shunhui, Zhang, Pengcheng

“…The widespread adoption of DNNs in NLP software has highlighted the need for robustness. Researchers proposed various automatic testing techniques for…”
Get full text

LibreLog: Accurate and Efficient Unsupervised Log Parsing Using Open-Source Large Language Models by Ma, Zeyang, Kim, Dong Jae, Chen, Tse-Hsun Peter

“… Traditional syntax-based log parsers are efficient and effective, but they often experience decreased accuracy when processing logs that deviate from the predefined rules…”
Get full text

Quality Assurance of Generative Dialog Models in an Evolving Conversational Agent Used for Swedish Language Practice by Borg, Markus, Bengtsson, Johan, Osterling, Harald, Hagelborn, Alexander, Gagner, Isabella, Tomaszewski, Piotr

“… While quality assurance of natural language processing applications is complex, we provide initial steps toward an automated framework for machine learning model selection in the context…”
Get full text

Large Language Model for Qualitative Research: A Systematic Mapping Study by Barros, Caua Ferreira, Azevedo, Bruna Borges, Graciano Neto, Valdemar Vicente, Kassab, Mohamad, Kalinowski, Marcos, Do Nascimento, Hugo Alexandre D., Bandeira, Michelle C.G.S.P.

“… and prone to subjectivity. Large Language Models (LLMs), powered by advanced generative AI, have emerged as transformative tools capable of automating and enhancing qualitative analysis…”
Get full text

Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection by Wahle, Jan Philip, Ruas, Terry, Meuschke, Norman, Gipp, Bela

“…Neural language models such as BERT allow for human-like text paraphrasing. This ability threatens academic integrity, as it aggravates identifying machine-obfuscated plagiarism…”
Get full text

Testing Machine Translation via Referential Transparency by He, Pinjia, Meister, Clara, Su, Zhendong

“… To address this problem, we introduce referentially transparent inputs (RTIs), a simple, widely applicable methodology for validating…”
Get full text

Poster: Extracting and Annotating Mental Health Forum Corpus: A Comprehensive Validation Pipeline by Jonnalagadda, Rohith Sundar, Azmee, Abm Adnan, Attota, Dinesh, Al Hafiz Khan, Md Abdullah, Pei, Yong, Nandan, Monica

“…This research emphasizes the essential role of mental health forums as vital online communities providing solace, support, and resources for individuals…”
Get full text

Integrating a dialog component into a framework for spoken language understanding by Weigelt, Sebastian, Hey, Tobias, Landhäußer, Mathias

“… Creating reactive spoken language interfaces requires skills in natural language processing…”
Get full text