Arrow Research search

Author name cluster

Teodora Baluta

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
2 author rows

Possible papers

2

NeurIPS Conference 2025 Conference Paper

Model Provenance Testing for Large Language Models

  • Ivica Nikolic
  • Teodora Baluta
  • Prateek Saxena

Large language models are increasingly customized through fine-tuning and other adaptations, creating challenges in enforcing licensing terms and managing downstream impacts such as protecting intellectual property or identifying vulnerabilities. We address this challenge by developing a framework for testing model provenance. Our approach is based on the key observation that real-world model derivations preserve significant similarities in model outputs that can be detected through statistical analysis. Using only black-box access to models, we employ multiple hypothesis testing to compare model similarities against a baseline established by unrelated models. On two comprehensive real-world benchmarks spanning models from 30M to 4B parameters and comprising over 600 models, our tester achieves 90-95% precision and 80-90% recall in identifying derived models. These results demonstrate the viability of systematic provenance verification in production environments even when only API access is available.

PDF Details

SAT Conference 2023 Conference Paper

Explaining SAT Solving Using Causal Reasoning

  • Jiong Yang 0002
  • Arijit Shaw
  • Teodora Baluta
  • Mate Soos
  • Kuldeep S. Meel

The past three decades have witnessed notable success in designing efficient SAT solvers, with modern solvers capable of solving industrial benchmarks containing millions of variables in just a few seconds. The success of modern SAT solvers owes to the widely-used CDCL algorithm, which lacks comprehensive theoretical investigation. Furthermore, it has been observed that CDCL solvers still struggle to deal with specific classes of benchmarks comprising only hundreds of variables, which contrasts with their widespread use in real-world applications. Consequently, there is an urgent need to uncover the inner workings of these seemingly weak yet powerful black boxes. In this paper, we present a first step towards this goal by introducing an approach called {CausalSAT}, which employs causal reasoning to gain insights into the functioning of modern SAT solvers. {CausalSAT} initially generates observational data from the execution of SAT solvers and learns a structured graph representing the causal relationships between the components of a SAT solver. Subsequently, given a query such as whether a clause with low literals blocks distance (LBD) has a higher clause utility, {CausalSAT} calculates the causal effect of LBD on clause utility and provides an answer to the question. We use {CausalSAT} to quantitatively verify hypotheses previously regarded as "rules of thumb" or empirical findings, such as the query above or the notion that clauses with high LBD experience a rapid drop in utility over time. Moreover, {CausalSAT} can address previously unexplored questions, like which branching heuristic leads to greater clause utility in order to study the relationship between branching and clause management. Experimental evaluations using practical benchmarks demonstrate that {CausalSAT} effectively fits the data, verifies four "rules of thumb", and provides answers to three questions closely related to implementing modern solvers.

Details
v2026.09.13