activity
20242026
collaborators

8 papers

cs.CL2026

uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking

Simon Lupart, Kidist Amde Mekonnen, Zahra Abbasiantaeb +1

This report describes our participation in SemEval-2026 Task 8 on multi-turn retrieval and question answering. The task evaluates conversational systems across four domains (financ…

cs.IR2026

The Multilingual Curse at the Retrieval Layer: Evidence from Amharic

Yosef Worku Alemneh, Kidist Amde Mekonnen, Maarten de Rijke

Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often take…

cs.IR2026

Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval

Kidist Amde Mekonnen, Yongkang Li, Yubao Tang +2

Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to…

cs.IR2026

A Parametric Memory Head for Continual Generative Retrieval

Kidist Amde Mekonnen, Yubao Tang, Maarten de Rijke

Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries. While this model-as-ind…

cs.IR2025

Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval

Kidist Amde Mekonnen, Yosef Worku Alemneh, Maarten de Rijke

Neural retrieval methods using transformer-based pre-trained language models have advanced multilingual and cross-lingual retrieval. However, their effectiveness for low-resource,…

cs.IR2025

Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval

Kidist Amde Mekonnen, Yubao Tang, Maarten de Rijke

Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task, allowing for…