Harald Steck

Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation

2025

Large Language Models (LLMs) are revolutionizing conversational recommender systems (CRS) by effectively indexing item content, understanding complex conversational contexts, and generating relevant item titles. However, the autoregressive nature of LLMs, which outputs item titles as …

From Reviews to Dialogues: Active Synthesis for Zero-Shot LLM-based Conversational Recommender System

2025 · arXiv (Cornell University)

Conversational recommender systems (CRS) typically require extensive domain-specific conversational datasets, yet high costs, privacy concerns, and data-collection challenges severely limit their availability. Although Large Language Models (LLMs) demonstrate strong zero-shot recommendation capabilities, practical applications often …

Calibrated recommendations

2018

When a user has watched, say, 70 romance movies and 30 action movies, then it is reasonable to expect the personalized list of recommended movies to be comprised of about 70% romance and 30% action …

Embarrassingly Shallow Autoencoders for Sparse Data

2019

Combining simple elements from the literature, we define a linear model that is geared toward sparse data, in particular implicit feedback data for recommender systems. We show that its training objective has a closed-form solution, …

Large Language Models as Zero-Shot Conversational Recommenders

2023

In this paper, we present empirical studies on conversational recommendation tasks using representative large language models in a zero-shot setting with three primary contributions. (1) Data: To gain insights into model behavior in "in-the-wild" conversational …