Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
DN Palacio, D Rodriguez-Cardenas, A Velasco… - arxiv preprint arxiv …, 2024 - arxiv.org
Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more
interpretable an LLM is, the more trustworthy it becomes. However, current techniques for …
interpretable an LLM is, the more trustworthy it becomes. However, current techniques for …
Transformer-based approaches to sentiment detection
The use of transfer learning methods is largely responsible for the present breakthrough in
Natural Learning Processing (NLP) tasks across multiple domains. In order to solve the …
Natural Learning Processing (NLP) tasks across multiple domains. In order to solve the …
Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code?
A Velasco, DN Palacio… - Proceedings of the …, 2024 - dl.acm.org
This paper discusses the limitations of evaluating Masked Language Models (MLMs) in
code completion tasks. We highlight that relying on accuracy-based measurements may …
code completion tasks. We highlight that relying on accuracy-based measurements may …
Beyond Accuracy: Evaluating Source Code Capabilities in Large Language Models for Software Engineering
A Velasco - Proceedings of the 2024 IEEE/ACM 46th International …, 2024 - dl.acm.org
This dissertation aims to introduce interpretability techniques to comprehensively evaluate
the performance of Large Language Models (LLMs) in software engineering tasks, beyond …
the performance of Large Language Models (LLMs) in software engineering tasks, beyond …
Transformer-Based Approaches to Sentiment Detection Check for updates Olumide Ebenezer Ojo, Hoang Thang Ta®, Alexander Gelbukh, Hiram Calvo, Olaronke …
H Calvo - Recent Developments and the New Directions of …, 2023 - books.google.com
The use of transfer learning methods is largely responsible for the present breakthrough in
Natural Learning Processing (NLP) tasks across multiple domains. In order to solve the …
Natural Learning Processing (NLP) tasks across multiple domains. In order to solve the …
[PDF][PDF] LLM による慣用句の言語間翻訳を用いたコード入力の支援
宮原和也， 山崎徹郎， 千葉滋 - 情報処理学会論文誌 …, 2024 - static.csg.ci.iu-tokyo.ac.jp
複数言語を使い分けて開発する環境では, 言語間の慣用句の違いによってプログラマが混乱する
ことがあるため, 異言語の慣用句の使用を認識して, その修**候補を提示する入力支援の開発が …
ことがあるため, 異言語の慣用句の使用を認識して, その修**候補を提示する入力支援の開発が …