arXiv subjects

Ashutosh Trivedi

Publications and source records attributed to Ashutosh Trivedi.

At least 37 records · Page 2Linked to original sources

arXiv2025

Technical Challenges in Maintaining Tax Prep Software with Large Language Models

As the US tax law evolves to adapt to ever-changing politico-economic realities, tax preparation software plays a significant role in helping taxpayers navigate these complexities. The dynamic nature of tax regulations poses a significant challenge to accurately and timely maintaining tax software artifacts. The state-of-the-art in maintaining tax prep software is time-consuming and error-prone as it involves manual code analysis combined with an expert interpretation of tax law amendments. We posit that the rigor and formality of tax amendment language, as expressed in IRS publications, makes it amenable to automatic translation to executable specifications (code). Our research efforts focus on identifying, understanding, and tackling technical challenges in leveraging Large Language Models (LLMs), such as ChatGPT and Llama, to faithfully extract code differentials from IRS publications and automatically integrate them with the prior version of the code to automate tax prep software maintenance.

cs.SE↗

arXiv2025

Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments

This paper introduces an open-source benchmark for evaluating Vision-Language Models (VLMs) on Optical Character Recognition (OCR) tasks in dynamic video environments. We present a curated dataset containing 1,477 manually annotated frames spanning diverse domains, including code editors, news broadcasts, YouTube videos, and advertisements. Three state of the art VLMs - Claude-3, Gemini-1.5, and GPT-4o are benchmarked against traditional OCR systems such as EasyOCR and RapidOCR. Evaluation metrics include Word Error Rate (WER), Character Error Rate (CER), and Accuracy. Our results highlight the strengths and limitations of VLMs in video-based OCR tasks, demonstrating their potential to outperform conventional OCR models in many scenarios. However, challenges such as hallucinations, content security policies, and sensitivity to occluded or stylized text remain. The dataset and benchmarking framework are publicly available to foster further research.

cs.CV↗

arXiv2025

Fairness Testing through Extreme Value Theory

Data-driven software is increasingly being used as a critical component of automated decision-support systems. Since this class of software learns its logic from historical data, it can encode or amplify discriminatory practices. Previous research on algorithmic fairness has focused on improving average-case fairness. On the other hand, fairness at the extreme ends of the spectrum, which often signifies lasting and impactful shifts in societal attitudes, has received significantly less emphasis. Leveraging the statistics of extreme value theory (EVT), we propose a novel fairness criterion called extreme counterfactual discrimination (ECD). This criterion estimates the worst-case amounts of disadvantage in outcomes for individuals solely based on their memberships in a protected group. Utilizing tools from search-based software engineering and generative AI, we present a randomized algorithm that samples a statistically significant set of points from the tail of ML outcome distributions even if the input dataset lacks a sufficient number of relevant samples. We conducted several experiments on four ML models (deep neural networks, logistic regression, and random forests) over 10 socially relevant tasks from the literature on algorithmic fairness. First, we evaluate the generative AI methods and find that they generate sufficient samples to infer valid EVT distribution in 95% of cases. Remarkably, we found that the prevalent bias mitigators reduce the average-case discrimination but increase the worst-case discrimination significantly in 5% of cases. We also observed that even the tail-aware mitigation algorithm -- MiniMax-Fairness -- increased the worst-case discrimination in 30% of cases. We propose a novel ECD-based mitigator that improves fairness in the tail in 90% of cases with no degradation of the average-case discrimination.

cs.SE↗

arXiv2024

Transfer Learning for Control Systems via Neural Simulation Relations

Transfer learning is an umbrella term for machine learning approaches that leverage knowledge gained from solving one problem (the source domain) to improve speed, efficiency, and data requirements in solving a different but related problem (the target domain). The performance of the transferred model in the target domain is typically measured via some notion of loss function in the target domain. This paper focuses on effectively transferring control logic from a source control system to a target control system while providing approximately similar behavioral guarantees in both domains. However, in the absence of a complete characterization of behavioral specifications, this problem cannot be captured in terms of loss functions. To overcome this challenge, we use (approximate) simulation relations to characterize observational equivalence between the behaviors of two systems. Simulation relations ensure that the outputs of both systems, equipped with their corresponding controllers, remain close to each other over time, and their closeness can be quantified {\it a priori}. By parameterizing simulation relations with neural networks, we introduce the notion of \emph{neural simulation relations}, which provides a data-driven approach to transfer any synthesized controller, regardless of the specification of interest, along with its proof of correctness. Compared with prior approaches, our method eliminates the need for a closed-loop mathematical model and specific requirements for both the source and target systems. We also introduce validity conditions that, when satisfied, guarantee the closeness of the outputs of two systems equipped with their corresponding controllers, thus eliminating the need for post-facto verification. We demonstrate the effectiveness of our approach through case studies involving a vehicle and a double inverted pendulum.

eess.SY↗

arXiv2024

Show, Don't Tell: Learning Reward Machines from Demonstrations for Reinforcement Learning-Based Cardiac Pacemaker Synthesis

An (artificial cardiac) pacemaker is an implantable electronic device that sends electrical impulses to the heart to regulate the heartbeat. As the number of pacemaker users continues to rise, so does the demand for features with additional sensors, adaptability, and improved battery performance. Reinforcement learning (RL) has recently been proposed as a performant algorithm for creative design space exploration, adaptation, and statistical verification of cardiac pacemakers. The design of correct reward functions, expressed as a reward machine, is a key programming activity in this process. In 2007, Boston Scientific published a detailed description of their pacemaker specifications. This document has since formed the basis for several formal characterizations of pacemaker specifications using real-time automata and logic. However, because these translations are done manually, they are challenging to verify. Moreover, capturing requirements in automata or logic is notoriously difficult. We posit that it is significantly easier for domain experts, such as electrophysiologists, to observe and identify abnormalities in electrocardiograms that correspond to patient-pacemaker interactions. Therefore, we explore the possibility of learning correctness specifications from such labeled demonstrations in the form of a reward machine and training an RL agent to synthesize a cardiac pacemaker based on the resulting reward machine. We leverage advances in machine learning to extract signals from labeled demonstrations as reward machines using recurrent neural networks and transformer architectures. These reward machines are then used to design a simple pacemaker with RL. Finally, we validate the resulting pacemaker using properties extracted from the Boston Scientific document.

cs.LG↗

arXiv2024

Metamorphic Debugging for Accountable Software

As the laws have become more complicated and enormous, the role of software systems in navigating and understanding these intricacies has become more critical. Given their socio-economic and legally critical implications, ensuring software accountability -- encompassing qualities such as legal compliance, explainability, perceptions of procedural justice, fairness of outcomes, and confidentiality/privacy -- is of paramount social importance. Moreover, software that accurately interprets its requirements, complies with legal standards and upholds social fairness can serve as a surrogate for legal and social norms, enabling policymakers to inquire about the law as seamlessly as a software engineer conducts a test. However, ensuring software accountability faces three key challenges: i) Translating legalese into formal specifications, ii) Lack of a definitive 'truth' for queries (the oracle problem), and iii) Scarcity of trustworthy datasets due to privacy and legal concerns. Drawing from the experiences in debugging U.S. tax preparation software, we propose that these challenges can be tackled by focusing on relational specifications. While the exact output for a given input may be unknown, the relationship between the outputs of two related inputs may be easier to express. This observation resembles i) the legal doctrine of precedent, meaning that similar cases must yield similar rulings; and ii) metamorphic relation (MR) in software engineering that requires a specific relation between software inputs and outputs. We propose metamorphic debugging as the foundation for detecting, explaining, and repairing socio-legal software for these relations. We showcase recent results that leverage metamorphic debugging to detect and explain accountability bugs in tax prep and poverty management software systems.

cs.SE↗

arXiv2024

Anticipating Oblivious Opponents in Stochastic Games

We present an approach for systematically anticipating the actions and policies employed by \emph{oblivious} environments in concurrent stochastic games, while maximizing a reward function. Our main contribution lies in the synthesis of a finite \emph{information state machine} whose alphabet ranges over the actions of the environment. Each state of the automaton is mapped to a belief state about the policy used by the environment. We introduce a notion of consistency that guarantees that the belief states tracked by our automaton stays within a fixed distance of the precise belief state obtained by knowledge of the full history. We provide methods for checking consistency of an automaton and a synthesis approach which upon successful termination yields such a machine. We show how the information state machine yields an MDP that serves as the starting point for computing optimal policies for maximizing a reward function defined over plays. We present an experimental evaluation over benchmark examples including human activity data for tasks such as cataract surgery and furniture assembly, wherein our approach successfully anticipates the policies and actions of the environment in order to maximize the reward.

cs.AI↗

arXiv2024

LLMs as Probabilistic Minimally Adequate Teachers for DFA Learning

The emergence of intelligence in large language models (LLMs) has inspired investigations into their integration into automata learning. This paper introduces the probabilistic Minimally Adequate Teacher (pMAT) formulation, which leverages a probabilistic oracle that could give persistent errors randomly during answering the membership queries for deterministic finite automata (DFA) learning. Given the tendency of LLMs to produce hallucinatory content, we have developed techniques to improve answer accuracy and ensure the correctness of the learned automata. We propose the $\mathtt{Discrimination}$ prompt as well as the $\mathtt{Verification}$ prompt and explore their advantages over common prompts. Additionally, we compare DFA learning performance between the TTT algorithm and common active learning algorithms. To address the exponential number of persistent errors, we implement a dynamic query cache refinement algorithm that identifies and corrects conflicting queries by combining the active and passive learning algorithms. The empirical results demonstrate the robustness and efficiency of our approach, providing a theoretical foundation for automata learning with LLMs in the loop.

cs.FL↗

arXiv2024

Predicting Fairness of ML Software Configurations

This paper investigates the relationships between hyperparameters of machine learning and fairness. Data-driven solutions are increasingly used in critical socio-technical applications where ensuring fairness is important. Rather than explicitly encoding decision logic via control and data structures, the ML developers provide input data, perform some pre-processing, choose ML algorithms, and tune hyperparameters (HPs) to infer a program that encodes the decision logic. Prior works report that the selection of HPs can significantly influence fairness. However, tuning HPs to find an ideal trade-off between accuracy, precision, and fairness has remained an expensive and tedious task. Can we predict fairness of HP configuration for a given dataset? Are the predictions robust to distribution shifts? We focus on group fairness notions and investigate the HP space of 5 training algorithms. We first find that tree regressors and XGBoots significantly outperformed deep neural networks and support vector machines in accurately predicting the fairness of HPs. When predicting the fairness of ML hyperparameters under temporal distribution shift, the tree regressors outperforms the other algorithms with reasonable accuracy. However, the precision depends on the ML training algorithm, dataset, and protected attributes. For example, the tree regressor model was robust for training data shift from 2014 to 2018 on logistic regression and discriminant analysis HPs with sex as the protected attribute; but not for race and other training algorithms. Our method provides a sound framework to efficiently perform fine-tuning of ML training algorithms and understand the relationships between HPs and fairness.

cs.SE↗

arXiv2024

Transfer of Safety Controllers Through Learning Deep Inverse Dynamics Model

Control barrier certificates have proven effective in formally guaranteeing the safety of the control systems. However, designing a control barrier certificate is a time-consuming and computationally expensive endeavor that requires expert input in the form of domain knowledge and mathematical maturity. Additionally, when a system undergoes slight changes, the new controller and its correctness certificate need to be recomputed, incurring similar computational challenges as those faced during the design of the original controller. Prior approaches have utilized transfer learning to transfer safety guarantees in the form of a barrier certificate while maintaining the control invariant. Unfortunately, in practical settings, the source and the target environments often deviate substantially in their control inputs, rendering the aforementioned approach impractical. To address this challenge, we propose integrating \emph{inverse dynamics} -- a neural network that suggests required action given a desired successor state -- of the target system with the barrier certificate of the source system to provide formal proof of safety. In addition, we propose a validity condition that, when met, guarantees correctness of the controller. We demonstrate the effectiveness of our approach through three case studies.

eess.SY↗

arXiv2024

Integrating Explanations in Learning LTL Specifications from Demonstrations

This paper investigates whether recent advances in Large Language Models (LLMs) can assist in translating human explanations into a format that can robustly support learning Linear Temporal Logic (LTL) from demonstrations. Both LLMs and optimization-based methods can extract LTL specifications from demonstrations; however, they have distinct limitations. LLMs can quickly generate solutions and incorporate human explanations, but their lack of consistency and reliability hampers their applicability in safety-critical domains. On the other hand, optimization-based methods do provide formal guarantees but cannot process natural language explanations and face scalability challenges. We present a principled approach to combining LLMs and optimization-based methods to faithfully translate human explanations and demonstrations into LTL specifications. We have implemented a tool called Janaka based on our approach. Our experiments demonstrate the effectiveness of combining explanations with demonstrations in learning LTL specifications through several case studies.

cs.AI↗

arXiv2024

Closure Certificates

A barrier certificate, defined over the states of a dynamical system, is a real-valued function whose zero level set characterizes an inductively verifiable state invariant separating reachable states from unsafe ones. When combined with powerful decision procedures such as sum-of-squares programming (SOS) or satisfiability-modulo-theory solvers (SMT) barrier certificates enable an automated deductive verification approach to safety. The barrier certificate approach has been extended to refute omega-regular specifications by separating consecutive transitions of omega-automata in the hope of denying all accepting runs. Unsurprisingly, such tactics are bound to be conservative as refutation of recurrence properties requires reasoning about the well-foundedness of the transitive closure of the transition relation. This paper introduces the notion of closure certificates as a natural extension of barrier certificates from state invariants to transition invariants. We provide SOS and SMT based characterization for automating the search of closure certificates and demonstrate their effectiveness via a paradigmatic case study.

cs.LO↗

arXiv2024

A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs

Linear temporal logic (LTL) and omega-regular objectives -- a superset of LTL -- have seen recent use as a way to express non-Markovian objectives in reinforcement learning. We introduce a model-based probably approximately correct (PAC) learning algorithm for omega-regular objectives in Markov decision processes (MDPs). As part of the development of our algorithm, we introduce the epsilon-recurrence time: a measure of the speed at which a policy converges to the satisfaction of the omega-regular objective in the limit. We prove that our algorithm only requires a polynomial number of samples in the relevant parameters, and perform experiments which confirm our theory.

cs.LG↗

arXiv2024

Composing Copyless Streaming String Transducers

Streaming string transducers (SSTs) implement string-to-string transformations by reading each input word in a single left-to-right pass while maintaining fragments of potential outputs in a finite set of string variables. These variables get updated on transitions of the transducer, where they can be assigned new values described by concatenations of variables and output symbols. An SST is called copyless if every update is such that no variable occurs more than once amongst all of the assigned expressions. The transformations realized by copyless SSTs coincide with Courcelle's monadic second-order logic graph transducers (MSOTs) when restricted to string graphs. Copyless SSTs with nondeterminism are known to be equivalent to nondeterministic MSOTs as well. MSOTs, both deterministic and nondeterministic, are closed under composition. Given the equivalence of MSOTs and copyless SSTs, it is easy to see that copyless SSTs are also closed under composition. The original proof of this fact, however, was based on a direct construction to produce a composite copyless SST from two given copyless SSTs. A counterexample discovered by Joost Englefriet showed that this construction may produce copyful transducers. We revisit the original composition constructions for both deterministic and nondeterministic SSTs and show that, although they can introduce copyful updates, the resulting copyful behavior they exhibit is superficial. To characterize this mild copyful behavior, we define a subclass of copyful SSTs, called diamond-free SSTs, in which two copies of a common variable are never combined in any subsequent assignment. In order to recover a modified version of the original construction, we provide a method for producing an equivalent copyless SST from any diamond-free copyful SST.

cs.FL↗

arXiv2024

Analyzing the Effectiveness of Large Language Models on Text-to-SQL Synthesis

This study investigates various approaches to using Large Language Models (LLMs) for Text-to-SQL program synthesis, focusing on the outcomes and insights derived. Employing the popular Text-to-SQL dataset, spider, the goal was to input a natural language question along with the database schema and output the correct SQL SELECT query. The initial approach was to fine-tune a local and open-source model to generate the SELECT query. After QLoRa fine-tuning WizardLM's WizardCoder-15B model on the spider dataset, the execution accuracy for generated queries rose to a high of 61%. With the second approach, using the fine-tuned gpt-3.5-turbo-16k (Few-shot) + gpt-4-turbo (Zero-shot error correction), the execution accuracy reached a high of 82.1%. Of all the incorrect queries, most can be categorized into a seven different categories of what went wrong: selecting the wrong columns or wrong order of columns, grouping by the wrong column, predicting the wrong values in conditionals, using different aggregates than the ground truth, extra or too few JOIN clauses, inconsistencies in the Spider dataset, and lastly completely incorrect query structure. Most if not all of the queries fall into these categories and it is insightful to understanding where the faults still lie with LLM program synthesis and where they can be improved.

cs.AI↗

arXiv2023

Assume-Guarantee Reinforcement Learning

We present a modular approach to \emph{reinforcement learning} (RL) in environments consisting of simpler components evolving in parallel. A monolithic view of such modular environments may be prohibitively large to learn, or may require unrealizable communication between the components in the form of a centralized controller. Our proposed approach is based on the assume-guarantee paradigm where the optimal control for the individual components is synthesized in isolation by making \emph{assumptions} about the behaviors of neighboring components, and providing \emph{guarantees} about their own behavior. We express these \emph{assume-guarantee contracts} as regular languages and provide automatic translations to scalar rewards to be used in RL. By combining local probabilities of satisfaction for each component, we provide a lower bound on the probability of satisfaction of the complete system. By solving a Markov game for each component, RL can produce a controller for each component that maximizes this lower bound. The controller utilizes the information it receives through communication, observations, and any knowledge of a coarse model of other agents. We experimentally demonstrate the efficiency of the proposed approach on a variety of case studies.

cs.LG↗

arXiv2023

Omega-Regular Decision Processes

Regular decision processes (RDPs) are a subclass of non-Markovian decision processes where the transition and reward functions are guarded by some regular property of the past (a lookback). While RDPs enable intuitive and succinct representation of non-Markovian decision processes, their expressive power coincides with finite-state Markov decision processes (MDPs). We introduce omega-regular decision processes (ODPs) where the non-Markovian aspect of the transition and reward functions are extended to an omega-regular lookahead over the system evolution. Semantically, these lookaheads can be considered as promises made by the decision maker or the learning agent about her future behavior. In particular, we assume that, if the promised lookaheads are not met, then the payoff to the decision maker is $\bot$ (least desirable payoff), overriding any rewards collected by the decision maker. We enable optimization and learning for ODPs under the discounted-reward objective by reducing them to lexicographic optimization and learning over finite MDPs. We present experimental results demonstrating the effectiveness of the proposed reduction.

cs.LO↗

arXiv2023

On the Potential and Limitations of Few-Shot In-Context Learning to Generate Metamorphic Specifications for Tax Preparation Software

Due to the ever-increasing complexity of income tax laws in the United States, the number of US taxpayers filing their taxes using tax preparation software (henceforth, tax software) continues to increase. According to the U.S. Internal Revenue Service (IRS), in FY22, nearly 50% of taxpayers filed their individual income taxes using tax software. Given the legal consequences of incorrectly filing taxes for the taxpayer, ensuring the correctness of tax software is of paramount importance. Metamorphic testing has emerged as a leading solution to test and debug legal-critical tax software due to the absence of correctness requirements and trustworthy datasets. The key idea behind metamorphic testing is to express the properties of a system in terms of the relationship between one input and its slightly metamorphosed twinned input. Extracting metamorphic properties from IRS tax publications is a tedious and time-consuming process. As a response, this paper formulates the task of generating metamorphic specifications as a translation task between properties extracted from tax documents - expressed in natural language - to a contrastive first-order logic form. We perform a systematic analysis on the potential and limitations of in-context learning with Large Language Models(LLMs) for this task, and outline a research agenda towards automating the generation of metamorphic specifications for tax preparation software.

cs.SE↗