Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation (FORGE 2026 - Research Papers) - FORGE 2026

Sun 12 - Sat 18 April 2026 Rio de Janeiro, Brazil

co-located with ICSE 2026

Who

Laboni Sarker, Mara Downing, Achintya Desai, Tevfik Bultan

Track

FORGE 2026 Research Papers

Time Zone

The program is currently displayed in (GMT-03:00) Brasilia, Distrito Federal, Brazil.

Use conference time zone: (GMT-03:00) Brasilia, Distrito Federal, BrazilSelect other time zone

The GMT offsets shown reflect the offsets at the moment of the conference.

Time Band

By setting a time band, the program will dim events that are outside this time window. This is useful for (virtual) conferences with a continuous program (with repeated sessions).
The time band will also limit the events that are included in the personal iCalendar subscription service.

Display full programSpecify a time band

When

Mon 13 Apr 2026 11:06 - 11:18 at Oceania I - Session III - Code Generation & Migration Chair(s): Daniel Rodriguez-Cardenas

Laboni Sarker

University of California at Santa Barbara

United States

Mara Downing

Achintya Desai

University of California, Santa Barbara

Tevfik Bultan

University of California at Santa Barbara

United States

Time Zone

The program is currently displayed in (GMT-03:00) Brasilia, Distrito Federal, Brazil.

Use conference time zone: (GMT-03:00) Brasilia, Distrito Federal, BrazilSelect other time zone

The GMT offsets shown reflect the offsets at the moment of the conference.

Time Band

By setting a time band, the program will dim events that are outside this time window. This is useful for (virtual) conferences with a continuous program (with repeated sessions).
The time band will also limit the events that are included in the personal iCalendar subscription service.

Display full programSpecify a time band

Session Program

Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

	11:00 - 12:30	Session III - Code Generation & MigrationData and Benchmarking / Research Papers at Oceania I Chair(s): Daniel Rodriguez-Cardenas William & Mary

	11:00 6m Talk		Deep Graph-Language Fusion for Structure-Aware Code Generation Research Papers Mert Tiftikci TU Darmstadt; hessian.AI, Amir Molzam Sharifloo TU Darmstadt, Mira Mezini TU Darmstadt; hessian.AI; National Research Center for Applied Cybersecurity ATHENE, Mert Tiftikci Technical University of Darmstadt
	11:06 12m Talk		Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation Research Papers Laboni Sarker University of California at Santa Barbara, Mara Downing , Achintya Desai University of California, Santa Barbara, Tevfik Bultan University of California at Santa Barbara
	11:18 6m Talk		Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis Research Papers Dipin Khati William & Mary, Daniel Rodriguez-Cardenas William & Mary, Paul Pantzer William & Mary, Denys Poshyvanyk William & Mary
	11:24 12m Talk		Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics Research Papers Markus Borg CodeScene, Nadim Hagatulah Lund University, Adam Tornhill Codescene AB, Emma Söderberg Lund University Pre-print
	11:36 6m Talk		VHDL-Instruct: Training Open Dataset for LLMs Benchmarking and HDL Code Generation Data and Benchmarking Patrik Drazic University of Southern Denmark, Benaoumeur Senouci University of Southern Denmark, Boualem Benatallah Dublin City University Media Attached
	11:48 6m Talk		COMPASS: A Psychometrics-Guided Multi-Dimensional Benchmark for Code Generation Evaluation Data and Benchmarking James Meaden Codility, Markus Borg CodeScene Pre-print
	11:54 6m Talk		A Hybrid LLM-Guided Approach to Code Migration Using API-Derived Rules Research Papers Gabriel Vitor Klaumann Gubert Technische Hochschule Ingolstadt (THI), Stefan Kugele Technische Hochschule Ingolstadt, Munir Georges Technische Hochschule Ingolstadt (THI) Media Attached
	12:00 12m Talk		An Experience Report on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights Research Papers Zhili Zeng York University, Kimya Khakzad Shahandashti York University, Alvine Boaye Belle York University, Song Wang York University, Zhen Ming (Jack) Jiang York University
	12:12 6m Talk		MiG.4: A Curated Dataset of Library Migrations in Java and Python Data and Benchmarking Matheus Barbosa UFMG, Pedro Baptista UFMG, João Eduardo Montandon Universidade Federal de Minas Gerais (UFMG), MATHEUS LIMA Ufmg, Pedro Henrique Fernandes Baptista UFMG
	12:18 6m Talk		PromiseAwait: A Dataset of JavaScript Migrations from Promises to Async/Await Data and Benchmarking Rafael Araujo Magesty UFMG, João Eduardo Montandon Universidade Federal de Minas Gerais (UFMG), Rafael Magesty