Chirag Shah

Chirag Shah

Auto-generated profile, based on publicly available information

Chirag Shah

Information School, University of Washington, Seattle, WA, USA

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
3 October 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
SVSahil Verma
Sahil Verma
VBVarich Boonsanong
Varich Boonsanong
MHMinh Hoang
Minh Hoang
KHKeegan Hines
Keegan Hines
JDJohn Dickerson
John Dickerson
CSChirag Shah
Chirag Shah
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of machine learning models is essential to the development of trustworthy machine learning based systems. A burgeoning body of research seeks to define the goals and methods of explainability in machine learning. In this article, we seek to review and categorize research on counterfactual explanations , a specific class of explanation that provides a link between what could have happened had input to a model been changed in a particular way. Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries, making them appealing to fielded systems in high-impact areas such as finance and healthcare. Thus, we design a rubric with desirable properties of counterfactual explanation algorithms and comprehensively evaluate all currently proposed algorithms against that rubric. Our rubric provides easy comparison and comprehension of the advantages and disadvantages of different approaches and serves as an introduction to major research themes in this field. We also identify gaps and discuss promising research directions in the space of counterfactual explainability.

19 July 2010
Verified
Conference Paper
Open access
PDF file
CSChirag Shah
Chirag Shah
JPJefferey Pomerantz
Jefferey Pomerantz

1 December 2009 in Library & Information Science Research
Verified
Journal Article
Closed access
CSChirag Shah
Chirag Shah
SOSanghee Oh
Sanghee Oh
JOJung Sun Oh
Jung Sun Oh

20 July 2008
Verified
Conference Paper
Open access
PDF file
JPJeremy Pickens
Jeremy Pickens
GGGene Golovchinsky
Gene Golovchinsky
CSChirag Shah
Chirag Shah
PQPernilla Qvarfordt
Pernilla Qvarfordt
MBMaribeth Back
Maribeth Back
We describe a new approach to information retrieval: algorithmic mediation for intentional, synchronous collaborative exploratory search. Using our system, two or more users with a common information need search together, simultaneously. The collaborative system provides tools, user interfaces and, most importantly, algorithmically-mediated retrieval to focus, enhance and augment the team's search and communication activities. Collaborative search outperformed post hoc merging of similarly instrumented single user runs. Algorithmic mediation improved both collaborative search (allowing a team of searchers to find relevant information more efficiently and effectively), and exploratory search (allowing the searchers to find relevant information that cannot be found while working individually).

26 November 2013 in Journal of the Association for Information Science and Technology
Verified
Journal Article
Closed access
PDF file
CSChirag Shah
Chirag Shah

18 July 2023
Verified
Conference Paper
Open access
LLLizi Liao
Lizi Liao
GYGrace Hui Yang
Grace Hui Yang
CSChirag Shah
Chirag Shah
ChatGPT and similar large language model (LLM) based conversational agents have brought shock waves to the research world. Although astonished by their human-like performance, we find they share a significant weakness with many other existing conversational agents in that they all take a passive approach in responding to user queries. This limits their capacity to understand the users and the task better and to offer recommendations based on a broader context than a given conversation. Proactiveness is still missing in these agents, including their ability to initiate a conversation, shift topics, or offer recommendations that take into account a more extensive context. To address this limitation, this tutorial reviews methods for equipping conversational agents with proactive interaction abilities. The full-day tutorial is divided into four parts, including multiple interactive exercises. We will begin the tutorial with an interactive exercise and cover the design of existing conversational systems architecture and challenges. The content includes coverage of LLM-based recent advancements such as ChatGPT and Bard, along with reinforcement learning with human feedback (RLHF) technique. Then we will introduce the concept of proactive conversation agents and preset recent advancements in proactiveness of conversational agents, including actively driving conversations by asking questions, topic shifting, and methods that support strategic planning of conversation. Next, we will discuss important issues in conversational responses' quality control, including safety, appropriateness, language detoxication, hallucination, and alignment. Lastly, we will launch another interactive exercise and discussion with the audience to arrive at concluding remarks, prospecting open challenges and new directions. By exploring new techniques for enhancing conversational agents' proactive behavior to improve user engagement, this tutorial aims to help researchers and practitioners develop more effective conversational agents that can better understand and respond to user needs proactively and safely.