UVA-IRLab Team Presents Multi-Turn RAG System for SemEval-2026 Conversational Question Answering Task
A team from UvA IRLab submitted a retrieval-augmented generation (RAG) system to SemEval-2026 Task 8, targeting multi-turn conversational question answering across four domains. The system pairs learned sparse retrieval with large language model-based reranking and generation, using full conversational history at each step. The work addresses a key challenge in conversational AI: maintaining context across turns while handling queries that cannot be answered from available documents.
Researchers from UvA IRLab describe a multi-step pipeline for SemEval-2026 Task 8, a shared task evaluating conversational retrieval and question answering across finance, cloud documentation, government, and Wikipedia domains. Their approach uses learned sparse retrieval as the primary retrieval mechanism, chosen for its strong cross-domain generalization. LLMs are then employed for conversational query rewriting, pointwise and listwise reranking, and final response generation, with each component conditioned on the full conversation history. The system is also designed to handle unanswerable queries — cases where the document collection lacks sufficient evidence for a complete response. The pipeline is presented in a 9-page paper with 5 figures and 6 tables, submitted to the 20th International Workshop on Semantic Evaluation collocated with ACL 2026.
What's missing
The abstract does not report quantitative evaluation results or benchmark scores, making it impossible to assess how the system performs relative to baselines or other SemEval-2026 Task 8 participants. The specific sparse retrieval model used and the choice of LLM backbone are not identified in the abstract.
What different sources said
- arXiv cs.CLCenter
uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.