Measuring LLM Code Generation Stability via Structural Entropy

SONG, Yewei; SUN, Tiezhu; TANG, Xunzhu; RAJPUT, Prateek Kumar; BISSYANDE, Tegawendé; KLEIN, Jacques

Download

Unpublished conference/Abstract (Scientific congresses, symposiums and conference proceedings)

Measuring LLM Code Generation Stability via Structural Entropy

SONG, Yewei; SUN, Tiezhu; TANG, Xunzhu et al.

2025 • 40th IEEE/ACM International Conference on Automated Software Engineering

Peer reviewed

Permalink
https://hdl.handle.net/10993/66243

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

2508.14288v1.pdf

Author preprint (2.11 MB)

Creative Commons License - Attribution, ShareAlike

Download

All documents in ORBilu are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Disciplines :

Computer science

Author, co-author :

SONG, Yewei ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX

SUN, Tiezhu ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX

TANG, Xunzhu ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX

RAJPUT, Prateek Kumar ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX

BISSYANDE, Tegawendé ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX

KLEIN, Jacques ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX

External co-authors :

Language :

English

Title :

Measuring LLM Code Generation Stability via Structural Entropy

Publication date :

16 November 2025

Event name :

40th IEEE/ACM International Conference on Automated Software Engineering

Event organizer :

Association for Computational Linguistics

Event place :

Seoul, South Korea

Event date :

from 16 to 20 November 2025

Audience :

International

Peer reviewed :

Peer reviewed

Available on ORBilu :

since 05 November 2025

Statistics

Number of views

39 (2 by Unilu)

Number of downloads

18 (1 by Unilu)

More statistics