169 citations · 299 across the 17 of their papers we have counts for
20 papers
Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences
Scott Sanner, Krisztian Balog, Filip Radlinski +2
Traditional recommender systems leverage users' item preference history to recommend novel content that users may like. However, modern dialog interfaces that allow users to expres…
Large Language Models for User Interest Journeys
Konstantina Christakopoulou, Alberto Lalama, Cj Adams +10
Large language models (LLMs) have shown impressive capabilities in natural language understanding and generation. Their potential for deeper user understanding and improved persona…
KNNs of Semantic Encodings for Rating Prediction
Léo Laugier, Raghuram Vadapalli, Thomas Bonald +1
This paper explores a novel application of textual semantic similarity to user-preference representation for rating prediction. The approach represents a user's preferences as a gr…
Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs
Kelvin Guu, Albert Webson, Ellie Pavlick +3
Training data attribution (TDA) methods offer to trace a model's prediction on any given example back to specific influential training examples. Existing approaches do so by assign…
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Maximilian Mozes, Tolga Bolukbasi, Ann Yuan +3
Pretrained large language models (LLMs) are able to solve a wide variety of tasks through transfer learning. Various explainability methods have been developed to investigate their…
Towards Agile Text Classifiers for Everyone
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek +5
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digi…
Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis
Shayegan Omidshafiei, Andrei Kapishnikov, Yannick Assogba +2
Each year, expert-level performance is attained in increasingly-complex multiagent domains, where notable examples include Go, Poker, and StarCraft II. This rapid progression is ac…
On Natural Language User Profiles for Transparent and Scrutable Recommendation
Filip Radlinski, Krisztian Balog, Fernando Diaz +2
Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years. We focus on the challenge of supporting people's understa…
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
Nan Du, Yanping Huang, Andrew M. Dai +24
Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to ach…
Toxicity Detection can be Sensitive to the Conversational Context
Alexandros Xenos, John Pavlopoulos, Ion Androutsopoulos +3
User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets wi…
Augmenting the User-Item Graph with Textual Similarity Models
Federico López, Martin Scholz, Jessica Yung +3
This paper introduces a simple and effective form of data augmentation for recommender systems. A paraphrase similarity model is applied to widely available textual data, such as r…
Civil Rephrases Of Toxic Texts With Self-Supervised Transformers
Leo Laugier, John Pavlopoulos, Jeffrey Sorensen +1
Platforms that support online commentary, from social networks to news sites, are increasingly leveraging machine learning to assist their moderation efforts. But this process does…
Six Attributes of Unhealthy Conversation
Ilan Price, Jordan Gifford-Moore, Jory Fleming +6
We present a new dataset of approximately 44000 comments labeled by crowdworkers. Each comment is labelled as either 'healthy' or 'unhealthy', in addition to binary labels for the…
Toxicity Detection: Does Context Really Matter?
John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon +2
Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of th…
Classifying Constructive Comments
Varada Kolhatkar, Nithum Thain, Jeffrey Sorensen +2
We introduce the Constructive Comments Corpus (C3), comprised of 12,000 annotated news comments, intended to help build new tools for online communities to improve the quality of t…
Limitations of Pinned AUC for Measuring Unintended Bias
Daniel Borkan, Lucas Dixon, John Li +3
This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classificatio…
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
Daniel Borkan, Lucas Dixon, Jeffrey Sorensen +2
Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in…
WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community
Yiqing Hua, Cristian Danescu-Niculescu-Mizil, Dario Taraborelli +3
We present a corpus that encompasses the complete history of conversations between contributors to Wikipedia, one of the largest online collaborative communities. By recording the…
Conversations Gone Awry: Detecting Early Signs of Conversational Failure
Justine Zhang, Jonathan P. Chang, Cristian Danescu-Niculescu-Mizil +4
One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of pred…
Network Traffic Obfuscation and Automated Internet Censorship
Lucas Dixon, Thomas Ristenpart, Thomas Shrimpton
Internet censors seek ways to identify and block internet access to information they deem objectionable. Increasingly, censors deploy advanced networking tools such as deep-packet…