Jelena Mitrović
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jelena Mitrović has a total of 103 co-authors. Here are the top co-authors by number of shared publications:
- Michael Granitzer
University of Passau, Passau, Germany
36 shared publications - Laura Caspari
University of Passau, Passau, Germany
9 shared publications - Michael Dinzinger
University of Passau, Passau, Germany
9 shared publications - Saber Zerhoudi
University of Passau, Passau, Germany
9 shared publications - Kanishka Ghosh Dastidar
Interdisciplinary Transformation University, Linz, Austria
6 shared publications - Mehdi Ben Amor
University of Passau, Passau, Germany
5 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6057-6068
The Compaction Cliff in Long-Running AI Agent Memory
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6057-6068
Open AccessThe Compaction Cliff in Long-Running AI Agent Memory
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6839-6843
The Fellowship of the Query: Learning Retrieval Actions
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6839-6843
Open AccessThe Fellowship of the Query: Learning Retrieval Actions
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6977-6982
When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale
Dense retrieval is commonly evaluated on benchmarks that represent each document with a single embedding, even though real-world retrieval systems often index long documents that require chunking. In these settings, the chosen chunking method not only affects retrieval quality, but also indexing throughput, query latency, and memory usage. Prior comparisons of chunking strategies have mainly focused on retrieval performance, leaving operational trade-offs underexplored. To address these issues, we evaluate eight representative chunking strategies across two scalable corpora, three embedding models, and multiple corpus sizes, measuring both retrieval effectiveness and system-level costs. Our results show that computationally expensive methods rarely provide consistent gains over simpler chunking. Instead, the best performing strategy depends on the embedding model, dataset, corpus size, and target retrieval metric. Methods with similar performance can also differ substantially in operational cost, showing that chunking should be seen as a multi-objective design decision. Our code and datasets are available on GitHub. https://github.com/casparil/chunking-eval and Hugging Face. https://huggingface.co/datasets/PaDaS-Lab/kilt-nq. https://huggingface.co/datasets/PaDaS-Lab/CoRE.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6977-6982
Open AccessWhen Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale
Dense retrieval is commonly evaluated on benchmarks that represent each document with a single embedding, even though real-world retrieval systems often index long documents that require chunking. In these settings, the chosen chunking method not only affects retrieval quality, but also indexing throughput, query latency, and memory usage. Prior comparisons of chunking strategies have mainly focused on retrieval performance, leaving operational trade-offs underexplored. To address these issues, we evaluate eight representative chunking strategies across two scalable corpora, three embedding models, and multiple corpus sizes, measuring both retrieval effectiveness and system-level costs. Our results show that computationally expensive methods rarely provide consistent gains over simpler chunking. Instead, the best performing strategy depends on the embedding model, dataset, corpus size, and target retrieval metric. Methods with similar performance can also differ substantially in operational cost, showing that chunking should be seen as a multi-objective design decision. Our code and datasets are available on GitHub. https://github.com/casparil/chunking-eval and Hugging Face. https://huggingface.co/datasets/PaDaS-Lab/kilt-nq. https://huggingface.co/datasets/PaDaS-Lab/CoRE.
- 7 September 2026
- Published by Springer Nature
- p. 57-74
Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichment
- 7 September 2026
- Published by Springer Nature
- p. 57-74
Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichment
- Open Access
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 56-61
Bridging the Gap between Subsampled and Full-Corpus Evaluation
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 56-61
Open AccessBridging the Gap between Subsampled and Full-Corpus Evaluation
- Open Access
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 425-435
As We May Search
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 425-435
Open AccessAs We May Search
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2286-2296
NuggetIndex: Governed Atomic Retrieval for Maintainable RAG
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2286-2296
Open AccessNuggetIndex: Governed Atomic Retrieval for Maintainable RAG
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3733-3737
Query Performance Prediction under Corpus Growth in Dense Retrieval
LLM-based chatbots are increasingly augmented with retrieval mechanisms operating over web-scale corpora. Evaluating the effectiveness of these retrieval components is challenging, as explicit relevance judgments are often unavailable. Query performance prediction (QPP) addresses this limitation by providing unsupervised estimates of retrieval effectiveness. However, existing QPP methods assume a static corpus and do not account for the impact of corpus growth on query performance. In this work, we extend the QPP paradigm by studying query performance degradation under corpus inflation in dense retrieval systems. Using tiered corpora with fixed relevance judgments, we analyze how query effectiveness evolves as the corpus (index) size increases and evaluate the ability of established score-based and embedding-based post-retrieval QPP methods to predict such degradation. Our findings show that the reliability of these predictors is dependent on the dataset. We propose simple adaptations to established QPP measures, most notably a top-k vs background Wasserstein distance measure, which yield more consistent associations with degradation and outperform their original counterparts. These findings highlight limitations of several QPP approaches in large-scale, continuously expanding retrieval environments and motivate the development of corpus-growth-aware QPP measures.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3733-3737
Open AccessQuery Performance Prediction under Corpus Growth in Dense Retrieval
LLM-based chatbots are increasingly augmented with retrieval mechanisms operating over web-scale corpora. Evaluating the effectiveness of these retrieval components is challenging, as explicit relevance judgments are often unavailable. Query performance prediction (QPP) addresses this limitation by providing unsupervised estimates of retrieval effectiveness. However, existing QPP methods assume a static corpus and do not account for the impact of corpus growth on query performance. In this work, we extend the QPP paradigm by studying query performance degradation under corpus inflation in dense retrieval systems. Using tiered corpora with fixed relevance judgments, we analyze how query effectiveness evolves as the corpus (index) size increases and evaluate the ability of established score-based and embedding-based post-retrieval QPP methods to predict such degradation. Our findings show that the reliability of these predictors is dependent on the dataset. We propose simple adaptations to established QPP measures, most notably a top-k vs background Wasserstein distance measure, which yield more consistent associations with degradation and outperform their original counterparts. These findings highlight limitations of several QPP approaches in large-scale, continuously expanding retrieval environments and motivate the development of corpus-growth-aware QPP measures.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3138-3144
WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3138-3144
Open AccessWebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3523-3529
AgentSim: A Platform for Verifiable Agent-Trace Simulation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3523-3529
Open AccessAgentSim: A Platform for Verifiable Agent-Trace Simulation