RUMBA: Russian User Memory Benchmark
The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning. To address this, we introduce RUMBA (Russian User Memory BenchmArk) - a new benchmark for long-term conversational memory that provides a fine-grained taxonomy of memory-centric question types and a unified methodology accounting for semantic type, session scope, temporal reasoning, and the explicitness of temporal expressions. RUM
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Evaluating long-term memory limits in stateless LLM chatbots — feedback needed [D] →
- PossiblePossibly related (embedding) · 55%TRACE: open-source hierarchical memory for LLM agents, 82.5% on MemoryAgentBench’s EventQA using gpt-oss-20B [P] →
- PossiblePossibly related (embedding) · 53%The biggest problem with AI memory isn't recall—it's stale facts [P] →
- FuzzySimilar title/name (fuzzy) · 59%jeinlee1991/chinese-llm-benchmark →
“Fuzzy title match (0.73): “RUMBA: Russian User Memory Benchmark” ≈ “jeinlee1991/chinese-llm-benchmark””
- LinkedLinked via arxiv author · 85%Elizaveta Shevtsova →
“RUMBA: Russian User Memory Benchmark”
- LinkedLinked via arxiv author · 85%Inna Glebkina →
“RUMBA: Russian User Memory Benchmark”
- LinkedLinked via arxiv author · 85%Mark Baushenko →
“RUMBA: Russian User Memory Benchmark”
- LinkedLinked via arxiv author · 85%Pavel Gulyaev →
“RUMBA: Russian User Memory Benchmark”