RECONTEXT is a recursive evidence replay technique that improves long-context reasoning in LLMs by constructing and replaying a query-conditioned evidence pool before final generation.
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management , pages =
4 Pith papers cite this work, alongside 32 external citations. Polarity classification is still indexing.
4
Pith papers citing it
32
external citations · external index
years
2026 4representative citing papers
DGF explicitly models multiple mode-conditioned predictive distributions via Dirichlet-guided sampling and reward optimization to preserve dynamical features in time series forecasts.
Mixture-of-experts fusing multiple pretrained forecasters achieves strongest performance on influenza time series, with pretraining gains largest at longer horizons when domain-aligned and LLM methods underperforming.
citing papers explorer
-
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
RECONTEXT is a recursive evidence replay technique that improves long-context reasoning in LLMs by constructing and replaying a query-conditioned evidence pool before final generation.
-
Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting
DGF explicitly models multiple mode-conditioned predictive distributions via Dirichlet-guided sampling and reward optimization to preserve dynamical features in time series forecasts.
-
Understanding Key Features of Time Series Foundation Models from Epidemic Forecasting
Mixture-of-experts fusing multiple pretrained forecasters achieves strongest performance on influenza time series, with pretraining gains largest at longer horizons when domain-aligned and LLM methods underperforming.
- Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance