Krisztian Balog

Towards Reliable and Factual Response Generation: Detecting Unanswerable Questions in Information-Seeking Conversations

2024 · arXiv (Cornell University)

Generative AI models face the challenge of hallucinations that can undermine users' trust in such systems. We approach the problem of conversational information seeking as a two-step process, where relevant passages in a corpus are …

SIGIR 2024 Workshop on Simulations for Information Access (Sim4IA 2024)

2024

Simulations in various forms have been used to evaluate information access systems, like search engines, recommender systems, or conversational agents. In the form of the Cranfield paradigm, a simulation setup is well-known in the IR …

Exploiting Entity Linking in Queries for Entity Retrieval

2016

The premise of entity retrieval is to better answer search queries by returning specific entities instead of documents. Many queries mention particular entities; recognizing and linking them to the corresponding entry in a knowledge base …

Transparent, Scrutable and Explainable User Models for Personalized Recommendation

2019

Most recommender systems base their recommendations on implicit or explicit item-level feedback provided by users. These item ratings are combined into a complex user model, which then predicts the suitability of other items. While effective, …

Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences

2023

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. …