Filip Radlinski

Filip Radlinski

Auto-generated profile, based on publicly available information

Filip Radlinski

Google, United Kingdom

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
14 September 2023
Verified
Conference Paper
Open access
SSScott Sanner
Scott Sanner
KBKrisztian Balog
Krisztian Balog
FRFilip Radlinski
Filip Radlinski
BWBen Wedin
Ben Wedin
LDLucas Dixon
Lucas Dixon
Traditional recommender systems leverage users’ item preference history to recommend novel content that users may like. However, modern dialog interfaces that allow users to express language-based preferences offer a fundamentally different modality for preference input. Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods. To support this investigation, we collect a new dataset consisting of both item-based and language-based preferences elicited from users along with their ratings on a variety of (biased) recommended items and (unbiased) random items. Among numerous experimental results, we find that LLMs provide competitive recommendation performance for pure language-based preferences (no item preferences) in the near cold-start case in comparison to item-based CF methods, despite having no supervised training for this specific task (zero-shot) or only a few labels (few-shot). This is particularly promising as language-based preference representations are more explainable and scrutable than item-based or vector-based representations.

10 April 2024 in ACM Transactions on Recommender Systems
Verified
Journal Article
Open access
IKIvica Kostric
Ivica Kostric
KBKrisztian Balog
Krisztian Balog
FRFilip Radlinski
Filip Radlinski
A key distinguishing feature of conversational recommender systems over traditional recommender systems is theirability to elicit user preferences using natural language. Currently, the predominant approach to preference elicitation is to ask questions directly about items or item attributes. Users searching for recommendations may not have deep knowledge of the available options in a given domain. As such, they might not be aware of key attributes or desirable values for them. However, in many settings, talking about the planned use of items does not present any difficulties, even for those that are new to a domain. In this article, we propose a novel approach to preference elicitation by asking implicit questions based on item usage. As one of the main contributions of this work, we develop a multi-stage data annotation protocol using crowdsourcing, to create a high-quality labeled training dataset. Another main contribution is the development of four models for the question generation task: two template-based baseline models and two neural text-to-text models. The template-based models use heuristically extracted common patterns found in the training data, while the neural models use the training data to learn to generate questions automatically. Using common metrics from machine translation for automatic evaluation, we show that our approaches are effective in generating elicitation questions, even with limited training data. We further employ human evaluation for comparing the generated questions using both pointwise and pairwise evaluation designs. We find that the human evaluation results are consistent with the automatic ones, allowing us to draw conclusions about the quality of the generated questions with certainty. Finally, we provide a detailed analysis of cases where the models show their limitations.

8 March 2021
Verified
Conference Paper
Open access
JPJavier Parapar
Javier Parapar
FRFilip Radlinski
Filip Radlinski
Personalized recommender systems rely on knowledge of user preferences to produce recommendations. While those preferences are often obtained from past user interactions with the recommendation catalog, in some situations such observations are insufficient or unavailable. The most widely studied case is with new users, although other similar situations arise where explicit preference elicitation is valuable. At the same time, a seemingly disparate challenge is that there is a well-known popularity bias in many algorithmic approaches to recommender systems. The most common way of addressing this challenge is diversification, which tends to be applied to the output of a recommender algorithm, prior to items being presented to users. We tie these two problems together, showing a tight relationship. Our results show that popularity bias in preference elicitation contributes to popularity bias in recommendation. In particular, most elicitation methods directly optimize only for the relevance of recommendations that would result from collected preferences. This focus on recommendation accuracy biases the preferences collected. We demonstrate how diversification can instead be applied directly at elicitation time. Our model diversifies the preferences elicited using Multi-Armed Bandits, a classical exploration-exploitation framework from reinforcement learning. This leads to a broader understanding of users' preferences, and improved diversity and serendipity of recommendations, without necessitating post-hoc debiasing corrections.

30 April 2023
Verified
Conference Paper
Open access
VFValeria Fionda
Valeria Fionda
OHOlaf Hartig
Olaf Hartig
RAReyhaneh Abdolazimi
Reyhaneh Abdolazimi
SASihem Amer-Yahia
Sihem Amer-Yahia
HCHongzhi Chen
Hongzhi Chen
WZWenwu Zhu
Wenwu Zhu
This paper summarizes the content of the 28 tutorials that have been given at The Web Conference 2023.

18 July 2023
Verified
Conference Paper
Open access
ACArun Tejasvi Chaganty
Arun Tejasvi Chaganty
MLMegan Leszczynski
Megan Leszczynski
SZShu Zhang
Shu Zhang
RGRavi Ganti
Ravi Ganti
KBKrisztian Balog
Krisztian Balog
FRFilip Radlinski
Filip Radlinski
Users in consumption domains, like music, are often able to more efficiently provide preferences over a set of items (e.g. a playlist or radio) than over single items (e.g. songs). Unfortunately, this is an underexplored area of research, with most existing recommendation systems limited to understanding preferences over single items. Curating an item set exponentiates the search space that recommender systems must consider (all subsets of items!): this motivates conversational approaches-where users explicitly state or refine their preferences and systems elicit preferences in natural language-as an efficient way to understand user needs. We call this task conversational item set curation and present a novel data collection methodology that efficiently collects realistic preferences about item sets in a conversational setting by observing both item-level and set-level feedback. We apply this methodology to music recommendation to build the Conversational Playlist Curation Dataset (CPCD), where we show that it leads raters to express preferences that would not be otherwise expressed. Finally, we propose a wide range of conversational retrieval models as baselines for this task and evaluate them on the dataset.

19 April 2023
Verified
Conference Paper
Open access
KBKrisztian Balog
Krisztian Balog
FRFilip Radlinski
Filip Radlinski
APAndrey Petrov
Andrey Petrov
Despite the potential impact of explanations on decision making, there is a lack of research on quantifying their effect on users’ choices. This paper presents an experimental protocol for measuring the degree to which positively or negatively biased explanations can lead to users choosing suboptimal recommendations. Key elements of this protocol include a preference elicitation stage to allow for personalizing recommendations, manual identification and extraction of item aspects from reviews, and a controlled method for introducing bias through the combination of both positive and negative aspects. We study explanations in two different textual formats: as a list of item aspects and as fluent natural language text. Through a user study with 129 participants, we demonstrate that explanations can significantly affect users’ selections and that these findings generalize across explanation formats.