49 citations · 55 across the 11 of their papers we have counts for
12 papers
Signals in the Noise: Decoding Unexpected Engagement Patterns on Twitter
Yulin Yu, Houming Chen, Daniel Romero +1
Social media platforms offer users multiple ways to engage with content--likes, retweets, and comments--creating a complex signaling system within the attention economy. While prev…
Dual Debiasing for Noisy In-Context Learning for Text Generation
Siqi Liang, Sumyeong Ahn, Paramveer S. Dhillon +1
In context learning (ICL) relies heavily on high quality demonstrations drawn from large annotated corpora. Existing approaches detect noisy annotations by ranking local perplexiti…
Policy Learning with a Natural Language Action Space: A Causal Approach
Bohan Zhang, Yixin Wang, Paramveer S. Dhillon
This paper introduces a novel causal framework for multi-stage decision-making in natural language action spaces where outcomes are only observed after a sequence of actions. While…
Recommendation and Temptation
Md Sanzeed Anwar, Paramveer S. Dhillon, Grant Schoenebeck
Traditional recommender systems based on revealed preferences often fail to capture the fundamental duality in user behavior, where consumption choices are driven by both inherent…
Causal Inference for Human-Language Model Collaboration
Bohan Zhang, Yixin Wang, Paramveer S. Dhillon
In this paper, we examine the collaborative dynamics between humans and language models (LMs), where the interactions typically involve LMs proposing text segments and humans editi…
Filter Bubble or Homogenization? Disentangling the Long-Term Effects of Recommendations on User Consumption Patterns
Md Sanzeed Anwar, Grant Schoenebeck, Paramveer S. Dhillon
Recommendation algorithms play a pivotal role in shaping our media choices, which makes it crucial to comprehend their long-term impact on user behavior. These algorithms are often…
Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models
Paramveer S. Dhillon, Somayeh Molaei, Jiaqi Li +3
Advances in language modeling have paved the way for novel human-AI co-writing experiences. This paper explores how varying levels of scaffolding from large language models (LLMs)…
Ranking & Reweighting Improves Group Distributional Robustness
Yachuan Liu, Bohan Zhang, Qiaozhu Mei +1
Recent work has shown that standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on underrepresented gro…
Modeling Dynamic User Interests: A Neural Matrix Factorization Approach
Paramveer Dhillon, Sinan Aral
In recent years, there has been significant interest in understanding users' online content consumption patterns. But, the unstructured, high-dimensional, and dynamic nature of suc…
Two Step CCA: A new spectral method for estimating vector models of words
Paramveer Dhillon, Jordan Rodu, Dean Foster +1
Unlabeled data is often used to learn representations which can be used to supplement baseline features in a supervised learner. For example, for text applications where the words…
A Risk Comparison of Ordinary Least Squares vs Ridge Regression
Paramveer S. Dhillon, Dean P. Foster, Sham M. Kakade +1
We compare the risk of ridge regression to a simple variant of ordinary least squares, in which one simply projects the data onto a finite dimensional subspace (as specified by a P…
Transfer Learning Using Feature Selection
Paramveer S. Dhillon, Dean Foster, Lyle Ungar
We present three related ways of using Transfer Learning to improve feature selection. The three methods address different problems, and hence share different kinds of information…