BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Mohammad Reza Mousavi

Mohammad Reza Mousavi contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Software EngineeringArtificial IntelligenceLogic in Computer Science

Trust snapshot

Quick read

Trust 17 - UnverifiedVerification L1Unclaimed author
4works
0followers
3topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

4 published item(s)

preprint2026arXiv

(How) Do Large Language Models Understand High-Level Message Sequence Charts?

Large Language Models (LLMs) are being employed widely to automate tasks across the software development life-cycle. It is, however, unclear whether these tasks are performed consistently with respect to the semantics of the artefacts being handled. This question is particularly under-researched concerning architectural design specification. In this paper, we address this question for High-Level Message Sequence Charts (HMSCs). These are visual models with a rigorous formal semantics that have been used for various purposes, including as a foundation for Sequence Diagrams in the Unified Modelling Language (UML). We examine whether LLMs "understand" the semantics of HMSCs by examining three LLMs (Gemini-3, GPT-5.4, and Qwen-3.6) on how they perform 129 semantic tasks ranging from querying basic semantic constructs in HMSCs (i.e., events and their ordering) to semantic-preserving abstractions and compositions, and calculating the set of traces and trace-equivalent labelled transition systems. The results show that LLMs only have a modest understanding of the formal semantics of HMSCs (ca. 52% overall accuracy), with great variability across different semantic concepts: while LLMs seem to understand the basic semantic concepts of MSCs (ca. 88% accuracy), they struggle with semantic reasoning in tasks involving abstraction and composition (ca. 36% accuracy) and traces and LTSs (ca. 42% accuracy). In particular, all three LLMs struggle with the notions of co-region and explicit causal dependencies and never employed them in semantic-preserving transformations.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

FairMedQA: Benchmarking Bias in Large Language Models for Medical Question Answering

Large language models (LLMs) are approaching expert-level performance in medical question answering (QA), demonstrating strong potential to improve public healthcare. However, underlying biases related to sensitive attributes such as sex and race pose life-critical risks. The extent to which such sensitive attributes affect diagnosis remains an open question and requires comprehensive empirical investigation. Additionally, even the latest Counterfactual Patient Variations (CPV) benchmark can hardly distinguish the bias levels of different LLMs. To further explore these dynamics, we propose a new benchmark, FairMedQA, and benchmark 12 representative LLMs. FairMedQA contains 4,806 counterfactual question pairs constructed from 801 clinical vignettes. Our results reveal substantial accuracy disparity ranging from 3 to 19 percentage points across sensitive demographic groups. Notably, FairMedQA exposes biases that are at least 12 percentage points larger than those identified by the latest CPV benchmark, presenting superior benchmarking sensitivity. Our results underscore an urgent need for targeted debiasing techniques and more rigorous, identity-aware validation protocols before LLMs can be safely integrated into practical clinical decision-support systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Benchmark for Active Learning of Variability-Intensive Systems

Behavioral models are the key enablers for behavioral analysis of Software Product Lines (SPL), including testing and model checking. Active model learning comes to the rescue when family behavioral models are non-existent or outdated. A key challenge on active model learning is to detect commonalities and variability efficiently and combine them into concise family models. Benchmarks and their associated metrics will play a key role in shaping the research agenda in this promising field and provide an effective means for comparing and identifying relative strengths and weaknesses in the forthcoming techniques. In this challenge, we seek benchmarks to evaluate the efficiency (e.g., learning time and memory footprint) and effectiveness (e.g., conciseness and accuracy of family models) of active model learning methods in the software product line context. These benchmark sets must contain the structural and behavioral variability models of at least one SPL. Each SPL in a benchmark must contain products that requires more than one round of model learning with respect to the basic active learning $L^{*}$ algorithm. Alternatively, tools supporting the synthesis of artificial benchmark models are also welcome.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Adaptive Behavioral Model Learning for Software Product Lines

Behavioral models enable the analysis of the functionality of software product lines (SPL), e.g., model checking and model-based testing. Model learning aims at constructing behavioral models for software systems in some form of a finite state machine. Due to the commonalities among the products of an SPL, it is possible to reuse the previously learned models during the model learning process. In this paper, an adaptive approach (the $\text{PL}^*$ method) for learning the product models of an SPL is presented based on the well-known $L^*$ algorithm. In this method, after model learning of each product, the sequences in the final observation table are stored in a repository which will be used to initialize the observation table of the remaining products to be learned. The proposed algorithm is evaluated on two open-source SPLs and the total learning cost is measured in terms of the number of rounds, the total number of resets and input symbols. The results show that for complex SPLs, the total learning cost for the $\text{PL}^*$ method is significantly lower than that of the non-adaptive learning method in terms of all three metrics. Furthermore, it is observed that the order in which the products are learned affects the efficiency of the $\text{PL}^*$ method. Based on this observation, we introduced a heuristic to determine an ordering which reduces the total cost of adaptive learning in both case studies.

0 citations0 reviewsNo code linkedOpen access