Author

Tomislav Duricic

h-index 5 View on Semantic Scholar

We have 2 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Aug 2026

Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation

These ReDial results support treating candidate generation, candidate-pool size, scoring policy, and decoding configuration as required reporting fields rather than implementation details, showing that measured reranker performance is highly sensitive to candidate generation.

A. Kapetanović, Tomislav Duricic, Andro Merćep et al. · 0 citations

Preprint Aug 2026

Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence

It is shown that prior scores, even when included only as context metadata, anchor judgments and systematically shift ratings toward their values, and effective mitigation must be validated for the intended model and task or domain.

A. Kapetanović, Kemal Altwlkany, Andro Merćep et al. · 0 citations