Biplav Srivastava

Biplav Srivastava

Auto-generated profile, based on publicly available information

Biplav Srivastava

University of South Carolina

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 May 2024 in Proceedings of the International Conference on Automated Planning and Scheduling
Verified
Journal Article
Open access
PDF file
VPVishal Pallagani
Vishal Pallagani
BMBharath Chandra Muppasani
Bharath Chandra Muppasani
KRKaushik Roy
Kaushik Roy
FFFrancesco Fabiano
Francesco Fabiano
ALAndrea Loreggia
Andrea Loreggia
ASAmit Sheth
Amit Sheth
Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive review of 126 papers, this paper investigates eight categories based on the unique applications of LLMs in addressing various aspects of planning problems: language translation, plan generation, model construction, multi-agent planning, interactive planning, heuristics optimization, tool integration, and brain-inspired planning. For each category, we articulate the issues considered and existing gaps. A critical insight resulting from our review is that the true potential of LLMs unfolds when they are integrated with traditional symbolic planners, pointing towards a promising neuro-symbolic approach. This approach effectively combines the generative aspects of LLMs with the precision of classical planning methods. By synthesizing insights from existing literature, we underline the potential of this integration to address complex planning challenges. Our goal is to encourage the ICAPS community to recognize the complementary strengths of LLMs and symbolic planners, advocating for a direction in automated planning that leverages these synergistic capabilities to develop more advanced and intelligent planning systems. We aim to keep the categorization of papers updated on https://ai4society.github.io/LLM-Planning-Viz/, a collaborative resource that allows researchers to contribute and add new literature to the categorization.

25 November 2023
Verified
Conference Paper
Open access
KLKausik Lakkaraju
Kausik Lakkaraju
SJSara E Jones
Sara E Jones
SVSai Krishna Revanth Vuruma
Sai Krishna Revanth Vuruma
VPVishal Pallagani
Vishal Pallagani
BMBharath C Muppasani
Bharath C Muppasani
BSBiplav Srivastava
Biplav Srivastava
As Large Language Model (LLM) based chatbots are becoming more accessible, users are relying on these chatbots for reliable and personalized recommendations in diverse domains, ranging from code generation to financial advisement. In this context, we set out to investigate how such systems perform in the personal finance domain, where financial inclusion has been an overarching stated aim of banks for decades. We test widely used LLM-based chatbots, ChatGPT and Bard, and compare their performance against SafeFinance, a rule-based chatbot built using the Rasa platform. The comparison is across two critical tasks: product discovery and multi-product interaction, where product refers to banking products like Credit Cards, Certificate of Deposits, and Checking Accounts. With this study, we provide interesting insights into the chatbots’ efficacy in financial advisement and their ability to provide fair treatment across different user groups. We find that both Bard and ChatGPT can make errors in retrieving basic online information, the responses they generate are inconsistent across different user groups, and they cannot be relied on for reasoning involving banking products. On the other hand, despite their limited generalization capabilities, rule-based chatbots like SafeFinance provide safe and reliable answers to users that can be traced back to their original source. Overall, although the outputs of the LLM-based chatbots are fluent and plausible, there are still critical gaps in providing consistent and reliable financial information.

15 September 2020 in IEEE Transactions on Technology and Society
Verified
Journal Article
Closed access
BSBiplav Srivastava
Biplav Srivastava
FRFrancesca Rossi
Francesca Rossi
SUSheema Usmani
Sheema Usmani
MBMariana Bernagozzi
Mariana Bernagozzi
In this paper, we address a setting where a conversation agent, also know as a chatbot, cannot be modified and its training data cannot be accessed, and yet a neutral party wants to assess and communicate its trustworthiness to a user in a way that is tailored to the user’s priorities over the various trust issues (such as bias, abusive language, information leakage, or inappropriate communication complexity). Such a rating can help users choose among alternative chatbots, developers test their systems, business leaders price their offerings, and regulators set policies. We describe a chatbot rating methodology that relies on separate rating modules for each trust issue, and on users’ priority orderings among the relevant trust issues, to generate an aggregate personalized rating for the trustworthiness of a chatbot. The method is independent of the specific trust issues and is parametric to the aggregation procedure, thereby allowing for seamless generalization. We illustrate its general use, integrate it with a live chatbot, and evaluate it on four dialog datasets and representative user profiles, validated with a user survey.

1 July 2019 in IBM Journal of Research and Development
Verified
Journal Article
Closed access
BSB. Srivastava
B. Srivastava
FRF. Rossi
F. Rossi

26 July 2021 in IEEE Internet Computing
Verified
Journal Article
Closed access
MBMariana Bernagozzi
Mariana Bernagozzi
BSBiplav Srivastava
Biplav Srivastava
FRFrancesca Rossi
Francesca Rossi
SUSheema Usmani
Sheema Usmani
AI systems that interact with humans, such as chatbots and language translators, have many useful applications. However, care must be put in addressing some concerns, such as the presence of bias, possible abusive language, and information leakage, that could hamper public trust in them. In this paper, we focus on gender bias in online translators, as recognized and rated by a third-party assessment who does not have access to the training data, and we propose a visualization approach for such rating. We then conduct a survey of how users perceive bias in translators, whether they appreciate the proposed bias rating visualization, and how they may use it to reason about bias-accuracy trade-offs

13 August 2021 in Patterns
Verified
Journal Article
Open access
BSBiplav Srivastava
Biplav Srivastava
Artificial intelligence (AI) technologies have long been positioned as a tool to provide crucial data-driven decision support to people. In this survey paper, I look at how collaboration assistants (chatbots for short), a type of AI that allows people to interact with them naturally (such as using speech, gesture, and text), have been used during a true global exigency—the COVID-19 pandemic. The key observation is that chatbots missed their “Apollo Moment” when at the time of need, they could have provided people with useful and life-saving contextual, personalized, and reliable decision support at a scale that the state-of-the-art makes possible. By “Apollo Moment”, I refer to the opportunity for a technology to attain the pinnacle of its impact. I review the chatbot capabilities that are feasible with existing methods, identify the potential that chatbots could have met, and highlight the use-cases they were deployed on, the challenges they faced, and gaps that persisted. Finally, I draw lessons that, if implemented, would make them more relevant in future health emergencies.