Mayank Kejriwal

IS Journal 2025 Journal Article

A Q-Learning Novelty Search Strategy for Evaluating Robustness of Deep Reinforcement Learning in Open-World Environments

• Shafkat Islam
• Min-Hsueh Chiu
• Trevor Bonjour
• Ruy de Oliveira
• Bharat Bhargava
• Mayank Kejriwal

Despite substantial progress in deep reinforcement learning (DRL), a systematic characterization of DRL agents’ robustness to unexpected events in the environment is relatively understudied. Such unexpected events (“novelties”), especially those that are more structural than parametric, may significantly deteriorate the performance of DRL agents, leading them to be unfit for open-world environments and applications. However, not all novelties affect an agent’s performance equally. Unfortunately, even with reasonable and constrained definitions of the problem, the space of all novelties can be (at least) exponential. Hence, an effective search strategy is required to find novelties that can adversely affect the agent. This article presents a formalism for this problem and proposes a deep Q-learning-based novelty search strategy that efficiently and systematically finds candidate (potentially complex) novelties with significant negative impact on a DRL agent. We conduct a detailed set of experiments in a stochastic multiagent game environment (Monopoly) with complex decision-making properties.

EAAI Journal 2025 Journal Article

Defining and evaluating decision and composite risk in language models applied to natural language inference

• Ke Shen
• Mayank Kejriwal

Despite their impressive performance, large language models (LLMs) are known to pose important risks. One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have in their inference. While the former is well studied, the latter is not, leading to an asymmetry in understanding the comprehensive risk of the model based on misplaced confidence. In this paper, we address this asymmetry by defining two types of risk (decision and composite risk), and proposing an experimental framework consisting of a two-level inference architecture and appropriate metrics for measuring such risks in both discriminative and generative LLMs. The first level relies on a decision rule that determines whether the underlying language model should abstain from inference. The second level (which applies if the model does not abstain) is the model’s inference. This framework has direct implications for error-sensitive LLM-based engineering applications where reliable decision-making is critical, such as healthcare and finance. Through detailed experiments on four natural language commonsense reasoning datasets using both an open-source ensemble-based transformer model and a generative LLM, we demonstrate the practical utility of our evaluation framework. Our results show that the framework can get an LLM to confidently respond to an extra 20. 1% of low-risk inference tasks that other methods might misclassify as high-risk, and skip 19. 8% of high-risk tasks, which would have been answered incorrectly.

AAAI Conference 2024 Short Paper

Multipartite Entity Resolution: Motivating a K-Tuple Perspective (Student Abstract)

• Adin Aberbach
• Mayank Kejriwal
• Ke Shen

Entity Resolution (ER) is the problem of algorithmically matching records, mentions, or entries that refer to the same underlying real-world entity. Traditionally, the problem assumes (at most) two datasets, between which records need to be matched. There is considerably less research in ER when k > 2 datasets are involved. The evaluation of such multipartite ER (M-ER) is especially complex, since the usual ER metrics assume (whether implicitly or explicitly) k < 3. This paper takes the first step towards motivating a k-tuple approach for evaluating M-ER. Using standard algorithms and k-tuple versions of metrics like precision and recall, our preliminary results suggest a significant difference compared to aggregated pairwise evaluation, which would first decompose the M-ER problem into independent bipartite problems and then aggregate their metrics. Hence, M-ER may be more challenging and warrant more novel approaches than current decomposition-based pairwise approaches would suggest.

EAAI Journal 2022 Journal Article

Transfer-based taxonomy induction over concept labels

• Mayank Kejriwal
• Ke Shen
• Chien-Chun Ni
• Nicolas Torzec

Given a domain-specific set of concepts, taxonomy induction is the problem of inducing a taxonomy from the set of concepts. The problem, despite having practical importance, has not received as much research attention, in contrast with related problems such as link prediction, due to its difficulty and lack of domain-specific benchmarks. In this paper, we present a principled approach for taxonomy induction in the e-commerce domain over a set of concept-labels, given background resources such as a pre-trained language representation learning model and examples of other taxonomies, induced over other concept-sets, but no example links for the target concept-set. Our approach, developed as an academic-industrial collaboration, is significantly more competitive than seven different baselines, including the transformer-based RoBERTa model, on three real-world and widely used e-commerce concept-sets.

AAAI Conference 2018 System Paper

Constructing Domain-Specific Search Engines With No Programming

• Mayank Kejriwal
• Pedro Szekely

We propose a demonstration of myDIG (my Domain-specific Insight Graphs), a system that allows non-technical domain experts, including those with no programming experience, to construct a domain-specific search engine over a raw corpus of webpages. myDIG has been developed and refined over multiple years under the DARPA MEMEX program, and has undergone rigorous user testing with actual domain experts from investigative agencies like the Securities and Exchange Commission (SEC). All components of myDIG are opensource, and the product of fundamental research.

IS Journal 2018 Journal Article

Investigative Knowledge Discovery for Combating Illicit Activities

• Mayank Kejriwal
• Pedro Szekely
• Craig Knoblock

Developing scalable, semi-automatic approaches to derive insights from a domain-specific Web corpus is a longstanding research problem in the knowledge discovery community. The problem is particularly challenging in illicit fields, such as human trafficking, where traditional assumptions concerning information representation are frequently violated. In this article, we describe an end-to-end investigative knowledge discovery system for illicit Web domains. We built and evaluated a prototype, involving separate components for information extraction, semantic modeling and query execution, on a real-world human trafficking Web corpus containing 1. 3 million pages, with promising results.

AAAI Conference 2015 Conference Paper

Entity Resolution in a Big Data Framework

• Mayank Kejriwal

AAAI Conference 2015 Conference Paper

Sorted Neighborhood for the Semantic Web

• Mayank Kejriwal