arXiv subjects

Zhanna Kaufman

Publications and source records attributed to Zhanna Kaufman.

5 recordsLinked to original sources

arXiv2026

Programmers Are Poor and Overconfident Judges of LLM-Generated Assertions

Code comprehension and code review are already critically important software engineering tasks, and the rising use of AI code generation tools is only increasing that importance. Generative AI has the possibility of supporting these activities, for example by augmenting code with assertions and natural-language explanations describing code behavior. However, little is known about how effective such support may be. We conduct a controlled experiment with 86 Python programmers and a follow-up think-aloud study to examine developers' ability to assess the correctness and completeness of generated assertions of varying quality, and to investigate how natural-language explanations influence these assessments. While programmers can somewhat accurately judge correct assertions (74% accuracy), they perform poorly when shown incorrect assertions (49% accuracy), despite reporting similar levels of confidence in both judgments. This difference in judgment accuracy is statistically significant (p < 0.001): the odds of a developer accurately judging a correct assertion was nearly three times higher than the odds of accurately judging an incorrect assertion (OR = 2.94). Surprisingly, natural-language explanations of assertions provided no overall benefit. Furthermore, low-quality explanations could impair specification assessment accuracy (p = 0.037, OR = 0.58) while simultaneously increasing developer confidence (p = 0.005, 3.99/5 vs. 4.25/5). Our findings suggest that, contrary to common assumptions, AI assistance may not improve the reliability of code comprehension and review. More broadly, our findings highlight the importance of helping developers evaluate machine-generated reliability artifacts, in addition to generating them.

cs.SE↗

arXiv2025

Your Model Is Unfair, Are You Even Aware? Inverse Relationship Between Comprehension and Trust in Explainability Visualizations of Biased ML Models

Systems relying on ML have become ubiquitous, but so has biased behavior within them. Research shows that bias significantly affects stakeholders' trust in systems and how they use them. Further, stakeholders of different backgrounds view and trust the same systems differently. Thus, how ML models' behavior is explained plays a key role in comprehension and trust. We survey explainability visualizations, creating a taxonomy of design characteristics. We conduct user studies to evaluate five state-of-the-art visualization tools (LIME, SHAP, CP, Anchors, and ELI5) for model explainability, measuring how taxonomy characteristics affect comprehension, bias perception, and trust for non-expert ML users. Surprisingly, we find an inverse relationship between comprehension and trust: the better users understand the models, the less they trust them. We investigate the cause and find that this relationship is strongly mediated by bias perception: more comprehensible visualizations increase people's perception of bias, and increased bias perception reduces trust. We confirm this relationship is causal: Manipulating explainability visualizations to control comprehension, bias perception, and trust, we show that visualization design can significantly (p < 0.001) increase comprehension, increase perceived bias, and reduce trust. Conversely, reducing perceived model bias, either by improving model fairness or by adjusting visualization design, significantly increases trust even when comprehension remains high. Our work advances understanding of how comprehension affects trust and systematically investigates visualization's role in facilitating responsible ML applications.

cs.HC↗

arXiv2024

QEDCartographer: Automating Formal Verification Using Reward-Free Reinforcement Learning

Formal verification is a promising method for producing reliable software, but the difficulty of manually writing verification proofs severely limits its utility in practice. Recent methods have automated some proof synthesis by guiding a search through the proof space using a theorem prover. Unfortunately, the theorem prover provides only the crudest estimate of progress, resulting in effectively undirected search. To address this problem, we create QEDCartographer, an automated proof-synthesis tool that combines supervised and reinforcement learning to more effectively explore the proof space. QEDCartographer incorporates the proofs' branching structure, enabling reward-free search and overcoming the sparse reward problem inherent to formal verification. We evaluate QEDCartographer using the CoqGym benchmark of 68.5K theorems from 124 open-source Coq projects. QEDCartographer fully automatically proves 21.4% of the test-set theorems. Previous search-based proof-synthesis tools Tok, Tac, ASTactic, Passport, and Proverbot9001, which rely only on supervised learning, prove 9.6%, 9.8%, 10.9%, 12.5%, and 19.8%, respectively. Diva, which combines 62 tools, proves 19.2%. Comparing to the most effective prior tool, Proverbot9001, QEDCartographer produces 34% shorter proofs 29% faster, on average over the theorems both tools prove. Together, QEDCartographer and non-learning-based CoqHammer prove 30.3% of the theorems, while CoqHammer alone proves 26.6%. Our work demonstrates that reinforcement learning is a fruitful research direction for improving proof-synthesis tools' search mechanisms.

cs.SE↗

arXiv2023

My Model is Unfair, Do People Even Care? Visual Design Affects Trust and Perceived Bias in Machine Learning

Machine learning technology has become ubiquitous, but, unfortunately, often exhibits bias. As a consequence, disparate stakeholders need to interact with and make informed decisions about using machine learning models in everyday systems. Visualization technology can support stakeholders in understanding and evaluating trade-offs between, for example, accuracy and fairness of models. This paper aims to empirically answer "Can visualization design choices affect a stakeholder's perception of model bias, trust in a model, and willingness to adopt a model?" Through a series of controlled, crowd-sourced experiments with more than 1,500 participants, we identify a set of strategies people follow in deciding which models to trust. Our results show that men and women prioritize fairness and performance differently and that visual design choices significantly affect that prioritization. For example, women trust fairer models more often than men do, participants value fairness more when it is explained using text than as a bar chart, and being explicitly told a model is biased has a bigger impact than showing past biased performance. We test the generalizability of our results by comparing the effect of multiple textual and visual design choices and offer potential explanations of the cognitive mechanisms behind the difference in fairness perception and trust. Our research guides design considerations to support future work developing visualization systems for machine learning.

cs.HC↗

arXiv2022

Passport: Improving Automated Formal Verification Using Identifiers

Formally verifying system properties is one of the most effective ways of improving system quality, but its high manual effort requirements often render it prohibitively expensive. Tools that automate formal verification, by learning from proof corpora to suggest proofs, have just begun to show their promise. These tools are effective because of the richness of the data the proof corpora contain. This richness comes from the stylistic conventions followed by communities of proof developers, together with the logical systems beneath proof assistants. However, this richness remains underexploited, with most work thus far focusing on architecture rather than making the most of the proof data. In this paper, we develop Passport, a fully-automated proof-synthesis tool that systematically explores how to most effectively exploit one aspect of that proof data: identifiers. Passport enriches a predictive Coq model with three new encoding mechanisms for identifiers: category vocabulary indexing, subword sequence modeling, and path elaboration. We compare Passport to three existing base tools which Passport can enhance: ASTactic, Tac, and Tok. In head-to-head comparisons, Passport automatically proves 29% more theorems than the best-performing of these base tools. Combining the three Passport-enhanced tools automatically proves 38% more theorems than the three base tools together, without Passport's enhancements. Finally, together, these base tools and Passport-enhanced tools prove 45% more theorems than the combined base tools without Passport's enhancements. Overall, our findings suggest that modeling identifiers can play a significant role in improving proof synthesis, leading to higher-quality software.

cs.PL↗