Search Results for author:
Found 35 papers, 3 papers with code
LLM-Driven Usefulness Labeling for IR Evaluation
In the information retrieval (IR) domain, evaluation plays a crucial role in optimizing search experiences and supporting diverse user intents.
Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversations
The ability to identify and acquire missing information is a critical component of effective decision making and problem solving.
Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations
Our results on three real-world datasets show a significant reduction in weak users and improved robustness to subpopulations without disproportionately escalating costs.
Agents Are Not Enough
In the midst of the growing integration of Artificial Intelligence (AI) into various aspects of our lives, agents are experiencing a resurgence.
How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold
We seek to determine the point at which a model was trained on enough instances to imitate a concept -- the imitation threshold.
Trusting Your AI Agent Emotionally and Cognitively: Development and Validation of a Semantic Differential Scale for AI Trust
Trust is not just a cognitive issue but also an emotional one, yet the research in human-AI interactions has primarily focused on the cognitive route of trust development.
How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions
We prompt different LLMs with a series of advice requests based on 5 Hofstede Cultural Dimensions -- a quantifiable way of representing the values of a country.
Do LLMs Exhibit Human-Like Reasoning? Evaluating Theory of Mind in LLMs for Open-Ended Responses
Theory of Mind (ToM) reasoning entails recognizing that other individuals possess their own intentions, emotions, and thoughts, which is vital for guiding one's own thought processes.
Panmodal Information Interaction
While our focus is search and chat, with learnings from insights from a survey of over 100 individuals who have recently performed common tasks on these two modalities, we also present a more general vision for the future of information interaction using multiple modalities and the emergent capabilities of GenAI.
Efficient and Responsible Adaptation of Large Language Models for Robust Top-k Recommendations
Our results on three real-world datasets show a significant reduction in weak users and improved robustness of RSs to sub-populations $(\approx12\%)$ and overall performance without disproportionately escalating costs.
The Use of Generative Search Engines for Knowledge Work and Complex Tasks
Until recently, search engines were the predominant method for people to access online information.
TnT-LLM: Text Mining at Scale with Large Language Models
Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application.
ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs
In the midst of widespread misinformation and disinformation through social media and the proliferation of AI-generated texts, it has become increasingly difficult for people to validate and trust information they encounter.
LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop
A case study using questions from the TruthfulQA dataset demonstrates that we can generate a reliable set of probes from one LLM that can be used to audit inconsistencies in a different LLM.
AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach
AuditLLM's primary function is to audit a given LLM by deploying multiple probes derived from a single question, thus detecting any inconsistencies in the model's comprehension or performance.
From Prompt Engineering to Prompt Science With Human in the Loop
We need a more scientific approach to using LLMs in our research.
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
We find that CleanCLIP, even with extensive hyperparameter tuning, is ineffective in poison removal when stronger pre-training objectives are used.
Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification
This undesirable property is the root cause of the manifestation of spurious correlations, which render models unreliable and prone to failure in the presence of distribution shifts.
Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models
Our new method is able to (1) identify weak decision boundaries for such classes; (2) construct search queries for Google as well as text for generating images through DALL-E 2 and Stable Diffusion; and (3) show how these newly captured training samples could alleviate population bias issue.
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
The traditional Dialogue State Tracking (DST) problem aims to track user preferences and intents in user-agent conversations.
Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies
However, using LLMs to generate a user intent taxonomy and apply it for log analysis can be problematic for two main reasons: (1) such a taxonomy is not externally validated; and (2) there may be an undesirable feedback loop.
Artificial Intelligence in Career Counseling: A Test Case with ResumAI
It is difficult to find good resources or schedule an appointment with a career counselor to help with editing a resume for a specific role.
RecRec: Algorithmic Recourse for Recommender Systems
To the best of our knowledge, this work is the first to conceptualize and empirically test a generalized framework for generating recourses for recommender systems.
Toward Connecting Speech Acts and Search Actions in Conversational Search Tasks
Then, the speech acts were fed to the model to predict the corresponding system-level search actions.
Taking Search to Task
For decades, scholars made a case for the role that a user's task plays in how and why that user engages in search and what a search system should do to assist.
RecXplainer: Amortized Attribute-based Personalized Explanations for Recommender Systems
We evaluate RecXplainer on five real-world and large-scale recommendation datasets using five different kinds of recommender systems to demonstrate the efficacy of RecXplainer in capturing users' preferences over item attributes and using them to explain recommendations.
Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systems
Current explanation generation models are found to exaggerate certain emotions without accurately capturing the underlying tone or the meaning.
EGCR: Explanation Generation for Conversational Recommendation
To the best of our knowledge, this is the first framework for explainable conversational recommendation on real-world datasets.
Users' Perception of Search Engine Biases and Satisfaction
We found out that users prefer results that are more consistent and relevant to the search queries.
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders.
Fairness-Aware Explainable Recommendation over Knowledge Graphs
There has been growing attention on fairness considerations recently, especially in the context of intelligent decision making systems.
Reading Protocol: Understanding what has been Read in Interactive Information Retrieval Tasks
In Interactive Information Retrieval (IIR) experiments the user's gaze motion on web pages is often recorded with eye tracking.
