The Impact of Critique on LLM-Based Model Generation from Natural Language: The Case of Activity Diagrams
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914173097607168 |
|---|---|
| author | Khamsepour, Parham Cole, Mark Ashraf, Ish Tan, DaYuan Puri, Sandeep Sabetzadeh, Mehrdad Nejati, Shiva |
| author_facet | Khamsepour, Parham Cole, Mark Ashraf, Ish Tan, DaYuan Puri, Sandeep Sabetzadeh, Mehrdad Nejati, Shiva |
| contents | Large Language Models (LLMs) show strong potential for automating model generation from natural-language descriptions. A common approach begins with an initial model generation, followed by an iterative critique-refine loop in which the model is evaluated for issues and refined based on those issues. This process needs to address: (1) structural correctness -- compliance with well-formedness rules -- and (2) semantic alignment -- accurate reflection of the intended meaning in the source text. We present LADEX (LLM-based Activity Diagram Extractor), a pipeline for deriving activity diagrams from natural-language process descriptions using an LLM-driven critique-refine process. Structural checks in LADEX can be performed either algorithmically or by an LLM, while alignment checks are performed by an LLM. We design five ablated variants of LADEX to study: (i) the impact of the critique-refine loop itself, (ii) the role of LLM-based semantic checks, and (iii) the comparative effectiveness of algorithmic versus LLM-based structural checks.
To evaluate LADEX, we compare generated diagrams with expert ground truths using a trace-based behavioural and an LLM-based matcher. This enables automated measurement of correctness (whether the generated activity diagram includes the ground-truth nodes) and completeness (how many of the ground-truth nodes the generated activity diagram covers). Experiments on two datasets -- a public-domain dataset and an industry dataset from our collaborator, Ciena -- indicate: (1) Both matchers yield similar completeness and correctness comparisons. (2) The critique-refine loop improves structural validity, correctness, and completeness compared to single-pass generation. (3) Activity diagrams refined based on algorithmic structural checks achieve structural consistency, whereas those refined based on LLM-based checks often still show structural inconsistencies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03463 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Impact of Critique on LLM-Based Model Generation from Natural Language: The Case of Activity Diagrams Khamsepour, Parham Cole, Mark Ashraf, Ish Tan, DaYuan Puri, Sandeep Sabetzadeh, Mehrdad Nejati, Shiva Software Engineering Large Language Models (LLMs) show strong potential for automating model generation from natural-language descriptions. A common approach begins with an initial model generation, followed by an iterative critique-refine loop in which the model is evaluated for issues and refined based on those issues. This process needs to address: (1) structural correctness -- compliance with well-formedness rules -- and (2) semantic alignment -- accurate reflection of the intended meaning in the source text. We present LADEX (LLM-based Activity Diagram Extractor), a pipeline for deriving activity diagrams from natural-language process descriptions using an LLM-driven critique-refine process. Structural checks in LADEX can be performed either algorithmically or by an LLM, while alignment checks are performed by an LLM. We design five ablated variants of LADEX to study: (i) the impact of the critique-refine loop itself, (ii) the role of LLM-based semantic checks, and (iii) the comparative effectiveness of algorithmic versus LLM-based structural checks. To evaluate LADEX, we compare generated diagrams with expert ground truths using a trace-based behavioural and an LLM-based matcher. This enables automated measurement of correctness (whether the generated activity diagram includes the ground-truth nodes) and completeness (how many of the ground-truth nodes the generated activity diagram covers). Experiments on two datasets -- a public-domain dataset and an industry dataset from our collaborator, Ciena -- indicate: (1) Both matchers yield similar completeness and correctness comparisons. (2) The critique-refine loop improves structural validity, correctness, and completeness compared to single-pass generation. (3) Activity diagrams refined based on algorithmic structural checks achieve structural consistency, whereas those refined based on LLM-based checks often still show structural inconsistencies. |
| title | The Impact of Critique on LLM-Based Model Generation from Natural Language: The Case of Activity Diagrams |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2509.03463 |