Jelena Mitrović

SOURCE: Scalable, Open, and Comprehensive Detection of Disinformation Campaigns on the Web

Faithful Query Resolution for Conversational Search

Conversational query rewriting makes context-dependent requests explicit for retrieval, but additional context can introduce an information need the user did not express. This raises a question about the interaction between query fidelity and retrieval breadth. This paper examines that interaction in behavior-adaptive...

The Fellowship of the Query: Learning Retrieval Actions

Overall, trajectory supervision improves action prediction and evidence-recording behaviour in this evaluated pipeline.

When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale

This work evaluates eight representative chunking strategies across two scalable corpora, three embedding models, and multiple corpus sizes, measuring both retrieval effectiveness and system-level costs and shows that computationally expensive methods rarely provide consistent gains over simpler chunking.

The Compaction Cliff in Long-Running AI Agent Memory

Knowledge Triage, a framework that classifies each line of an agent's knowledge base by type and routes each type through its own retention policy, is addressed, and AgentArtifactCorpus, the classifier, and the reference implementation are released.

Query Performance Prediction under Corpus Growth in Dense Retrieval

This work extends the QPP paradigm by studying query performance degradation under corpus inflation in dense retrieval systems and proposes simple adaptations to established QPP measures, most notably a top-k vs background Wasserstein distance measure, which yield more consistent associations with degradation and outpe...