An official website of the United States government
While mutation testing has been a topic of academic interest for decades, it is only recently that “real-world” developers, including industry leaders such as Google and Meta, have adopted mutation testing. We propose a new approach to the development of mutation testing tools, and in particular the core challenge ofgenerating mutants. Current practice tends towards two limited approaches to mutation generation: mutants are either (1) generated at the bytecode/IR level, and thus neither human readable nor adaptable to source-level features of languages or projects, or (2) generated at the source level by language-specific tools that are hard to write and maintain, and in fact are often abandoned by both developers and users. We propose instead that source-level mutation generation is a special case ofprogram transformationin general, and that adopting this approach allows for a single tool that can effectively generate source-level mutants for essentiallyanyprogramming language. Furthermore, by usingparser parser combinatorsmany of the seeming limitations of an any-language approach can be overcome, without the need to parse specific languages. We compare this new approach to mutation to existing tools, and demonstrate the advantages of using parser parser combinators to improve on a regular-expression based approach to generation. Finally, we show that our approach can provide effective mutant generation even for a language for which it lacks any language-specific operators, and that is not very similar in syntax to any language it has been applied to previously.
more »
« less
Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications
Language model applications are becoming increasingly popular and complex, often including features like tool usage and retrieval augmentation. However, existing frameworks for such applications are often opinionated, deciding for developers how their prompts ought to be formatted and imposing limitations on customizability and reproducibility. To solve this we present Kani: a lightweight, flexible, and model-agnostic open-source framework for building language model applications. Kani helps developers implement a variety of complex features by supporting the core building blocks of chat interaction: model interfacing, chat management, and robust function calling. All Kani core functions are easily overridable and well documented to empower developers to customize functionality for their own needs. Kani thus serves as a useful tool for researchers, hobbyists, and industry professionals alike to accelerate their development while retaining interoperability and fine-grained control.
more »
« less
- Award ID(s):
- 1928474
- PAR ID:
- 10563506
- Publisher / Repository:
- Empirical Methods in Natural Language Processing
- Date Published:
- Page Range / eLocation ID:
- 65 to 77
- Subject(s) / Keyword(s):
- LLMs open source python
- Format(s):
- Medium: X
- Location:
- Singapore, Singapore
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Large language models have recently been able to perform well in a wide variety of circumstances. In this work, we explore the possibility of large language models, specifically GPT-3, to write explanations for middle-school mathematics problems, with the goal of eventually using this process to rapidly generate explanations for the mathematics problems of new curricula as they emerge, shortening the time to integrate new curricula into online learning platforms. To generate explanations, two approaches were taken. The first approach attempted to summarize the salient advice in tutoring chat logs between students and live tutors. The second approach attempted to generate explanations using few-shot learning from explanations written by teachers for similar mathematics problems. After explanations were generated, a survey was used to compare their quality to that of explanations written by teachers. We test our methodology using the GPT-3 language model. Ultimately, the synthetic explanations were unable to outperform teacher written explanations. In the future more powerful large language models may be employed, and GPT-3 may still be effective as a tool to augment teachers’ process for writing explanations, rather than as a tool to replace them. The explanations, survey results, analysis code, and a dataset of tutoring chat logs are all available at https://osf.io/wh5n9/.more » « less
-
null (Ed.)Software developers use modern chat platforms to communicate about the status of a project and to coordinate development and release efforts, among other things. Developers also use chat platforms to ask technical questions to other developers. While some questions are project-specific and require an experienced developer familiar with the system to answer, many questions are rather general and may have been already answered by other developers on platforms such as the Q&A site StackOverflow. In this paper, we present GitterAns, a bot that can automatically detect when a developer asks a technical question in a chat and leverages the information present in Q&A forums to provide the developer with possible answers to their question. The results of a preliminary study indicate promising results, with GitterAns achieving an accuracy of 0.78 in identifying technical questions.more » « less
-
Large language models have recently been able to perform well in a wide variety of circumstances. In this work, we explore the possi- bility of large language models, specifically GPT-3, to write explanations for middle-school mathematics problems, with the goal of eventually us- ing this process to rapidly generate explanations for the mathematics problems of new curricula as they emerge, shortening the time to inte- grate new curricula into online learning platforms. To generate expla- nations, two approaches were taken. The first approach attempted to summarize the salient advice in tutoring chat logs between students and live tutors. The second approach attempted to generate explanations us- ing few-shot learning from explanations written by teachers for similar mathematics problems. After explanations were generated, a survey was used to compare their quality to that of explanations written by teachers. We test our methodology using the GPT-3 language model. Ultimately, the synthetic explanations were unable to outperform teacher written explanations. In the future more powerful large language models may be employed, and GPT-3 may still be effective as a tool to augment teachers’ process for writing explanations, rather than as a tool to replace them. The prompts, explanations, survey results, analysis code, and a dataset of tutoring chat logs are all available at BLINDED FOR REVIEW.more » « less
-
Large language models have recently been able to perform well in a wide variety of circumstances. In this work, we explore the possi- bility of large language models, specifically GPT-3, to write explanations for middle-school mathematics problems, with the goal of eventually us- ing this process to rapidly generate explanations for the mathematics problems of new curricula as they emerge, shortening the time to inte- grate new curricula into online learning platforms. To generate expla- nations, two approaches were taken. The first approach attempted to summarize the salient advice in tutoring chat logs between students and live tutors. The second approach attempted to generate explanations us- ing few-shot learning from explanations written by teachers for similar mathematics problems. After explanations were generated, a survey was used to compare their quality to that of explanations written by teachers. We test our methodology using the GPT-3 language model. Ultimately, the synthetic explanations were unable to outperform teacher written explanations. In the future more powerful large language models may be employed, and GPT-3 may still be effective as a tool to augment teach- ers’ process for writing explanations, rather than as a tool to replace them. The explanations, survey results, analysis code, and a dataset of tutoring chat logs are all available at https://osf.io/wh5n9/.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2023.nlposs-1.8
