Author name cluster

Ankit Shah

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.

12 papers

2 author rows

AAAI Conference 2026 Short Paper

ProRefine: Inference-Time Prompt Refinement with Textual Feedback (Student Abstract)

Deepak Pandita
Tharindu Cyril Weerasooriya
Ankit Shah
Isabelle Diana May-Xin Ng
Christopher M. Homan
Wei Wei

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications. These workflows depend critically on the prompts used to provide the roles models play in such workflows. Poorly designed prompts that fail even slightly to guide individual agents can lead to sub-optimal performance that may snowball within a system of agents, limiting their reliability and scalability. To address this important problem of inference-time prompt optimization, we introduce ProRefine, an innovative inference-time optimization method that uses an agentic loop of LLMs to generate and apply textual feedback. ProRefine dynamically refines prompts for multi-step reasoning tasks without additional training or ground truth labels. Evaluated on five benchmark mathematical reasoning datasets, ProRefine significantly surpasses zero-shot Chain-of-Thought baselines by 3 to 37 percentage points. This approach not only boosts accuracy but also allows smaller models to approach the performance of their larger counterparts. This highlights its potential for building cost-effective and powerful hybrid AI systems, thereby democratizing access to high-performing AI.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations

Hao Chen
Ankit Shah
Jindong Wang
Ran Tao
Yidong Wang
Xiang Li
Xing Xie
Masashi Sugiyama

Learning with reduced labeling standards, such as noisy label, partial label, and supplementary unlabeled data, which we generically refer to as imprecise label, is a commonplace challenge in machine learning tasks. Previous methods tend to propose specific designs for every emerging imprecise label configuration, which is usually unsustainable when multiple configurations of imprecision coexist. In this paper, we introduce imprecise label learning (ILL), a framework for the unification of learning with various imprecise label configurations. ILL leverages expectation-maximization (EM) for modeling the imprecise label information, treating the precise labels as latent variables. Instead of approximating the correct labels for training, it considers the entire distribution of all possible labeling entailed by the imprecise information. We demonstrate that ILL can seamlessly adapt to partial label learning, semi-supervised learning, noisy label learning, and, more importantly, a mixture of these settings, with closed-form learning objectives derived from the unified EM modeling. Notably, ILL surpasses the existing specified techniques for handling imprecise labels, marking the first practical and unified framework with robust and effective performance across various challenging settings. We hope our work will inspire further research on this topic, unleashing the full potential of ILL in wider scenarios where precise labels are expensive and complicated to obtain.

PDF Details DOI

IROS Conference 2024 Conference Paper

Lang2LTL-2: Grounding Spatiotemporal Navigation Commands Using Large Language and Vision-Language Models

Jason Xinyu Liu
Ankit Shah
George Konidaris 0001
Stefanie Tellex
David Paulius

Grounding spatiotemporal navigation commands to structured task specifications enables autonomous robots to understand a broad range of natural language and solve long-horizon tasks with safety guarantees. Prior works mostly focus on grounding spatial or temporally extended language for robots. We propose Lang2LTL-2, a modular system that leverages pretrained large language and vision-language models and multimodal semantic information to ground spatiotemporal navigation commands in novel city-scaled environments without retraining. Lang2LTL-2 achieves 93. 53% language grounding accuracy on a dataset of 21, 780 semantically diverse natural language commands in unseen environments. We run an ablation study to validate the need for different modalities. We also show that a physical robot equipped with the same system without modification can execute 50 semantically diverse natural language commands in both indoor and outdoor environments.

Details

ICRA Conference 2024 Conference Paper

Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents

Ziyi Yang
Shreyas Sundara Raman
Ankit Shah
Stefanie Tellex

Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during pretraining. However, while considerable effort has been made to teach the robot the "dos", the "don’ts" received relatively less attention. We argue that, for any practical usage, it is as crucial to teach the robot the "don’ts": conveying explicit instructions about prohibited actions, assessing the robot’s comprehension of these restrictions, and, most importantly, ensuring compliance. Moreover, verifiable safe operation is essential for deployments that satisfy worldwide standards such as ISO 61508, which defines standards for safely deploying robots in industrial factory environments worldwide. Aiming at deploying the LLM agents in a collaborative environment, we propose a queryable safety constraint module based on linear temporal logic (LTL) that simultaneously enables natural language (NL) to temporal constraints encoding, safety violation reasoning and explaining, and unsafe action pruning. To demonstrate the effectiveness of our system, we conducted experiments in VirtualHome environment and on a real robot. The experimental results show that our system strictly adheres to the safety constraints and scales well with complex safety constraints, highlighting its potential for practical utility.

Details

ICRA Conference 2024 Conference Paper

Skill Transfer for Temporal Task Specification

Jason Xinyu Liu
Ankit Shah
Eric Rosen
Mingxi Jia
George Konidaris 0001
Stefanie Tellex

Deploying robots in real-world environments, such as households and manufacturing lines, requires generalization across novel task specifications without violating safety constraints. Linear temporal logic (LTL) is a widely used task specification language with a compositional grammar that naturally induces commonalities among tasks while preserving safety guarantees. However, most prior work on reinforcement learning with LTL specifications treats every new task independently, thus requiring large amounts of training data to generalize. We propose LTL-Transfer, a zero-shot transfer algorithm that composes task-agnostic skills learned during training to safely satisfy a wide variety of novel LTL task specifications. Experiments in Minecraft-inspired domains show that after training on only 50 tasks, LTL-Transfer can solve over 90% of 100 challenging unseen tasks and 100% of 300 commonly used novel tasks without violating any safety constraints. We deployed LTL-Transfer at the task-planning level of a quadruped mobile manipulator to demonstrate its zero-shot transfer ability for fetch-and-deliver and navigation tasks.

Details

AAAI Conference 2021 Conference Paper

Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example

Serena Booth
Yilun Zhou
Ankit Shah
Julie Shah

Post-hoc explanation methods are gaining popularity for interpreting, understanding, and debugging neural networks. Most analyses using such methods explain decisions in response to inputs drawn from the test set. However, the test set may have few examples that trigger some model behaviors, such as high-conﬁdence failures or ambiguous classiﬁcations. To address these challenges, we introduce a ﬂexible model inspection framework: BAYES-TREX. Given a data distribution, BAYES-TREX ﬁnds in-distribution examples which trigger a speciﬁed prediction conﬁdence. We demonstrate several use cases of BAYES-TREX, including revealing highly con- ﬁdent (mis)classiﬁcations, visualizing class boundaries via ambiguous examples, understanding novel-class extrapolation behavior, and exposing neural network overconﬁdence. We use BAYES-TREX to study classiﬁers trained on CLEVR, MNIST, and Fashion-MNIST, and we show that this framework enables more ﬂexible holistic model analysis than just inspecting the test set. Code and supplemental material are available at https: //github. com/serenabooth/Bayes-TrEx.

PDF Details

TIST Journal 2020 Journal Article

Two Can Play That Game

Ankit Shah
Arunesh Sinha
Rajesh Ganesan
Sushil Jajodia
Hasan Cam

Cyber-security is an important societal concern. Cyber-attacks have increased in numbers as well as in the extent of damage caused in every attack. Large organizations operate a Cyber Security Operation Center (CSOC), which forms the first line of cyber-defense. The inspection of cyber-alerts is a critical part of CSOC operations (defender or blue team). Recent work proposed a reinforcement learning (RL) based approach for the defender’s decision-making to prevent the cyber-alert queue length from growing large and overwhelming the defender. In this article, we perform a red team (adversarial) evaluation of this approach. With the recent attacks on learning-based decision-making systems, it is even more important to test the limits of the defender’s RL approach. Toward that end, we learn several adversarial alert generation policies and the best response against them for various defender’s inspection policy. Surprisingly, we find the defender’s policies to be quite robust to the best response of the attacker. In order to explain this observation, we extend the earlier defender’s RL model to a game model with adversarial RL, and show that there exist defender policies that can be robust against any adversarial policy. We also derive a competitive baseline from the game theory model and compare it to the defender’s RL approach. However, when we go further to exploit the assumptions made in the Markov Decision Process (MDP) in the defender’s RL model, we discover an attacker policy that overwhelms the defender. We use a double oracle like approach to retrain the defender with episodes from this discovered attacker policy. This made the defender robust to the discovered attacker policy and no further harmful attacker policies were discovered. Overall, the adversarial RL and double oracle approach in RL are general techniques that are applicable to other RL usage in adversarial environments.

Details DOI

IJCAI Conference 2019 Conference Paper

Bayesian Inference of Linear Temporal Logic Specifications for Contrastive Explanations

Joseph Kim
Christian Muise
Ankit Shah
Shubham Agarwal
Julie Shah

Temporal logics are useful for providing concise descriptions of system behavior, and have been successfully used as a language for goal definitions in task planning. Prior works on inferring temporal logic specifications have focused on "summarizing" the input dataset - i. e. , finding specifications that are satisfied by all plan traces belonging to the given set. In this paper, we examine the problem of inferring specifications that describe temporal differences between two sets of plan traces. We formalize the concept of providing such contrastive explanations, then present BayesLTL - a Bayesian probabilistic model for inferring contrastive explanations as linear temporal logic (LTL) specifications. We demonstrate the robustness and scalability of our model for inferring accurate specifications from noisy data and across various benchmark planning domains.

PDF Details

IJCAI Conference 2019 Conference Paper

Learning Sound Events from Webly Labeled Data

Anurag Kumar
Ankit Shah
Alexander Hauptmann
Bhiksha Raj

In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims to remove human supervision altogether from the learning process. We first develop a method of obtaining labeled audio data from the web (albeit noisy), in which no manual labeling is involved. We then describe methods to efficiently learn from these webly labeled audio recordings. In our proposed system, WeblyNet, two deep neural networks co-teach each other to robustly learn from webly labeled data, leading to around 17% relative improvement over the baseline method. The method also involves transfer learning to obtain efficient representations.

PDF Details

NeurIPS Conference 2018 Conference Paper

Bayesian Inference of Temporal Task Specifications from Demonstrations

Ankit Shah
Pritish Kamath
Julie Shah
Shen Li

When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of an execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring true specifications with over 90% similarity between the inferred specification and the ground truth, both within a synthetic domain and a real-world table setting task.

PDF Details

TIST Journal 2018 Journal Article

Dynamic Optimization of the Level of Operational Effectiveness of a CSOC Under Adverse Conditions

Ankit Shah
Rajesh Ganesan
Sushil Jajodia
Hasan Cam

The analysts at a cybersecurity operations center (CSOC) analyze the alerts that are generated by intrusion detection systems (IDSs). Under normal operating conditions, sufficient numbers of analysts are available to analyze the alert workload. For the purpose of this article, this means that the cybersecurity analysts in each shift can fully investigate each and every alert that is generated by the IDSs in a reasonable amount of time and perform their normal tasks in a shift. Normal tasks include analysis time, time to attend training programs, report writing time, personal break time, and time to update the signatures on new patterns in alerts as detected by the IDS. There are several disruptive factors that occur randomly and can adversely impact the normal operating condition of a CSOC, such as (1) higher alert generation rates from a few IDSs, (2) new alert patterns that decrease the throughput of the alert analysis process, and (3) analyst absenteeism. The impact of the preceding factors is that the alerts wait for a long duration before being analyzed, which impacts the level of operational effectiveness (LOE) of the CSOC. To return the CSOC to normal operating conditions, the manager of a CSOC can take several actions, such as increasing the alert analysis time spent by analysts in a shift by canceling a training program, spending some of his own time to assist the analysts in alert investigation, and calling upon the on-call analyst workforce to boost the service rate of alerts. However, additional resources are limited in quantity over a 14-day work cycle, and the CSOC manager must determine when and how much action to take in the face of uncertainty, which arises from both the intensity and the random occurrences of the disruptive factors. The preceding decision by the CSOC manager is nontrivial and is often made in an ad hoc manner using prior experiences. This work develops a reinforcement learning (RL) model for optimizing the LOE throughout the entire 14-day work cycle of a CSOC in the face of uncertainties due to disruptive events. Results indicate that the RL model is able to assist the CSOC manager with a decision support tool to make better decisions than current practices in determining when and how much resource to allocate when the LOE of a CSOC deviates from the normal operating condition.

Details DOI

TIST Journal 2016 Journal Article

Dynamic Scheduling of Cybersecurity Analysts for Minimizing Risk Using Reinforcement Learning

Rajesh Ganesan
Sushil Jajodia
Ankit Shah
Hasan Cam

An important component of the cyber-defense mechanism is the adequate staffing levels of its cybersecurity analyst workforce and their optimal assignment to sensors for investigating the dynamic alert traffic. The ever-increasing cybersecurity threats faced by today’s digital systems require a strong cyber-defense mechanism that is both reactive in its response to mitigate the known risk and proactive in being prepared for handling the unknown risks. In order to be proactive for handling the unknown risks, the above workforce must be scheduled dynamically so the system is adaptive to meet the day-to-day stochastic demands on its workforce (both size and expertise mix). The stochastic demands on the workforce stem from the varying alert generation and their significance rate, which causes an uncertainty for the cybersecurity analyst scheduler that is attempting to schedule analysts for work and allocate sensors to analysts. Sensor data are analyzed by automatic processing systems, and alerts are generated. A portion of these alerts is categorized to be significant, which requires thorough examination by a cybersecurity analyst. Risk, in this article, is defined as the percentage of significant alerts that are not thoroughly analyzed by analysts. In order to minimize risk, it is imperative that the cyber-defense system accurately estimates the future significant alert generation rate and dynamically schedules its workforce to meet the stochastic workload demand to analyze them. The article presents a reinforcement learning-based stochastic dynamic programming optimization model that incorporates the above estimates of future alert rates and responds by dynamically scheduling cybersecurity analysts to minimize risk (i.e., maximize significant alert coverage by analysts) and maintain the risk under a pre-determined upper bound. The article tests the dynamic optimization model and compares the results to an integer programming model that optimizes the static staffing needs based on a daily-average alert generation rate with no estimation of future alert rates (static workforce model). Results indicate that over a finite planning horizon, the learning-based optimization model, through a dynamic (on-call) workforce in addition to the static workforce, (a) is capable of balancing risk between days and reducing overall risk better than the static model, (b) is scalable and capable of identifying the quantity and the right mix of analyst expertise in an organization, and (c) is able to determine their dynamic (on-call) schedule and their sensor-to-analyst allocation in order to maintain risk below a given upper bound. Several meta-principles are presented, which are derived from the optimization model, and they further serve as guiding principles for hiring and scheduling cybersecurity analysts. Days-off scheduling was performed to determine analyst weekly work schedules that met the cybersecurity system’s workforce constraints and requirements.

Details DOI