Follow @UoMpodcast for service updates and information.
S3 Seminar - Victor Braberman Author: Edoardo Manino Added on Sat Oct 12 13:05:00 BST 2024 Duration: 1:08:41 Date and time: 10 October @ 2pm BST Title: Tasks People Prompt: A Taxonomy of LLM Downstream Tasks in Software Verification and Falsification Approaches Abstract: Prompting has become one of the main approaches to leverage emergent capabilities of Large Language Models [Brown et al. NeurIPS 2020, Wei et al. TMLR 2022, Wei et al. NeurIPS 2022]. Recently, researchers and practitioners have been "playing" with prompts (e.g., In-Context Learning) to see how to make the most of pre-trained Language Models. By homogeneously dissecting more than a hundred articles, we investigate how software testing and verification research communities have leveraged LLMs capabilities. First, we validate that downstream tasks are adequate to convey a nontrivial modular blueprint of prompt-based proposals in scope. Moreover, we name and classify the concrete downstream tasks we recover in both validation research papers and solution proposals. In order to perform classification, mapping, and analysis, we also develop a novel downstream-task taxonomy. The main taxonomy requirement is to highlight commonalities while exhibiting variation points of task types that enable pinpointing emerging patterns in a varied spectrum of Software Engineering problems that encompasses testing, fuzzing, fault localization, vulnerability detection, static analysis, and program verification approaches. Avenues for future research are also discussed based on conceptual clusters induced by the taxonomy. Speaker: Victor Braberman is professor at Universidad de Buenos Aires and principal researcher at CONICET. He has been working on innovative uses of abstractions for the analysis, construction and understanding of software intensive systems. His research interests also include rigorously based requirement engineering, software verification, and the foundations for disciplined engineering based on Large Language Models. He serves regularly as PC/PB member and associate editor for flagship software engineering conferences and journals.  

Remove Video

Use this form to remove a podcast immediately






Remove Video





Subtitle request


Subtitle quality is dependant on a number of factors therefore accuracy cannot be guaranteed. For more information see mypodcasts.manchester.ac.uk/subtitles

Usernames are recorded for service monitoring purposes.





Subtitle request


The subtitle request has been submitted.

Please allow up to 24 hours for the subtitles to be published. For more information see mypodcasts.manchester.ac.uk/subtitles



Subtitle request


Subtitles are already available for this video.

To request new subtitles, contact podcasting@manchester.ac.uk



Embed Code
Video ID
Follow @UoMpodcast for service updates and information.