Still Fresh? Evaluating Temporal Drift in Retrieval Benchmarks

LongEval-Sci evaluates scientific retrieval under collection change, where a system should be effective on the current corpus and remain usable as documents accumulate over time. This paper reports both official Task 1 results and development diagnostics for LongEval-Sci 2026. We compare the official PyTerrier BM25 and Qwen3 dense baselines with full-text BM25, additive and router variants, temporal full-text retrieval, temporal+citation retrieval, RM3 query expansion, cross-encoder reranking, and reciprocal rank fusion (RRF). In the official DCTR evaluation, the temporalized full-text runs are our strongest submissions: FT BM25+temporal and FT BM25+temporal+citation obtain the best ARP on all three snapshots (0.285, 0.267, and 0.180 nDCG@10) and reduce snapshot-3 relative change from 0.481 for the BM25 pivot to 0.368. Citation features match the temporal-only variant but do not provide a measurable additional gain in the official summary. Our internal snapshot-1 diagnostics show a complementary pattern: full-text BM25 is the strongest single development retriever (DCTR nDCG@10 = 0.3302, MAP = 0.2853), RRF gives the best deep recall (Recall@1000 = 0.9667), and some uncalibrated overlays can sharply degrade top-rank quality. We therefore conclude that full-text retrieval is the strongest foundation, temporal integration can improve official longitudinal effectiveness when applied to that foundation, and citation evidence still requires cleaner ablation and calibration. Beyond ranking, we also report a qualitative weekly IR-system update-monitoring analysis based on ingestion velocity and stale-coverage drift.

Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language models (LLMs) by grounding responses in up-to-date evidence. Within the RAG pipeline, re-rankers play a pivotal role in selecting the most useful documents from retrieved candidates. However, existing benchmarks predominantly evaluate re-rankers in static settings and do not adequately assess performance under evolving information -- a critical gap, as real-world systems often must choose among temporally different pieces of evidence. To address this limitation, we introduce FRESCO (Factual Recency and Evolving Semantic COnflict), a benchmark for evaluating re-rankers in temporally dynamic contexts. By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance. Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete. We further investigate an instruction optimization framework to mitigate this issue. By identifying Pareto-optimal instructions that balance Evolving and Non-Evolving Knowledge tasks, we obtain gains of up to 27% on Evolving Knowledge tasks while maintaining competitive performance on Non-Evolving Knowledge tasks.

Retrieval-augmented generation (RAG) is often used to address outdated knowledge by providing external evidence. But retrieval helps only when that evidence is still valid. We identify a temporal alignment failure, stale-document poisoning, in which outdated evidence makes a model wrong despite answering correctly without retrieval. We construct a benchmark of 317 verified knowledge reversals across medicine, law, software, and platform policy, grounded in dated official sources. Across 12 models, recent medical reversals are harder than long-established ones. More importantly, outdated retrieval flips 30% of Llama and 37% of Qwen answers even without instructions to trust the document; explicit follow instructions raise these rates to 66% and 75%. Across four open models and four domains, poisoning ranges from 17-91%, while matched up-to-date evidence is followed in 97-100% of trials. To isolate temporal applicability, we keep the historical evidence unchanged across 50 reversals and vary only the evaluation date. A clear pattern emerges: dates alone produce only modest adaptation, but when models are explicitly told when the old evidence stops applying, the larger models switch to the appropriate answer almost perfectly. Causal interventions confirm that this validity information directly shapes the final decision. The same internal components also support broader comparison tasks, suggesting that temporal applicability can recruit a general reasoning mechanism used for other comparisons. Finally, a fixed recency-aware hybrid re-ranker reduces poisoning by 4.6-10.0 points when dates are accurate, with gains that depend on reliable temporal metadata. Reliable RAG therefore requires selective trust: models must determine not only what retrieved evidence says, but whether it still applies.