GINGER (Grounded Information Nugget-Based Generation of Responses), our response generation system, achieved the top performance in the Automated Generation task at TREC RAG’24, based on automatic evaluation with AutoNuggetizer. Check out the track’s initial results and the preprint of our paper describing GINGER!
IAI
Gabriel Iturra-Bocaz joins IAI
We welcome Gabriel Iturra-Bocaz as our new PhD student, who will focus his research on LLMs for information retrieval, under the supervision of Petra Galuscakova.
PhD position in Large Language Models for Recommendation
We have a PhD position in Large Language Models for Recommendation, funded by the NorwAI research-based innovation center. See the details on jobbnorge. Application deadline is Oct 31.
SIGIR-AP’24 full paper accepted
The paper Can Users Detect Biases or Factual Errors in Generated Responses in Conversational Information-Seeking? by Weronika Łajewska, Krisztian Balog, Damiano Spina, and Johanne Trippas has been accepted at the 2nd International ACM SIGIR Conference on Information Retrieval in the Asia Pacific (SIGIR-AP ’24). The preprint will follow soon.
CIKM’24 paper on Question Generation for Fact-Checking
QuestGen: Effectiveness of Question Generation Methods for Fact-Checking Applications by Ritvik Setty and Vinay Setty has been accepted at the 33rd ACM International Conference on Information and Knowledge Management (CIKM’24) as a short paper.
Best Paper Honorable Mention Award at ICTIR’24
The paper Towards a Formal Characterization of User Simulation Objectives in Conversational Information Access by Nolwenn Bernard and Krisztian Balog received the Best Paper Honorable Mention Award at the 14th International Conference on the Theory of Information Retrieval (ICTIR ’24). The paper is available here.
CUI’24 and ICTIR’24 papers on user simulation
Some recent paper acceptances on user simulation in conversational information access:
- Identifying Breakdowns in Conversational Recommender Systems using User Simulation — full paper at CUI ’24 by Nolwenn Bernard and Krisztian Balog [PDF]
- Towards a Formal Characterization of User Simulation Objectives in Conversational Information Access — full paper at ICTIR ’24 by Nolwenn Bernard and Krisztian Balog [PDF]
User Simulation for Evaluating Information Access Systems book
The book User Simulation for Evaluating Information Access Systems by Krisztian Balog and ChengXiang Zhai has been published by Foundations and Trends in Information Retrieval. This comprehensive monograph delves into the pivotal role of user simulation in assessing the effectiveness of information access systems, such as search engines, recommender systems, and conversational assistants. A preprint is available on arXiv.
PKG API presented at WWW’24
The PKG API is a tool for managing personal knowledge graphs (PKGs), which has been developed by our group (Nolwenn Bernard, Ivica Kostric, Weronika Łajewska, Krisztian Balog, Petra Galuscakova, Vinay Setty, and Martin G. Skjæveland). This work is a first step toward the realization of our proposed PKG ecosystem and has been presented at the 2024 ACM Web Conference, in Singapore. Have a look at the paper or the toolkit for more details.
Best Short Paper Award at ECIR’24
The paper Towards Reliable and Factual Response Generation: Detecting Unanswerable Questions in Information-seeking Conversations by Weronika Łajewska and Krisztian Balog has received the Best Short Paper Award at the 46th European Conference on Information Retrieval (ECIR ’24). You can read the paper here.