BM25 remains competitive in RAG benchmarks; ColBERT outperforms larger LLMs
antoine_chaffin · x · 2026-08-16
Antoine Chaffin highlights a recurring trend in RAG evaluations: classic BM25 often remains surprisingly competitive upon new benchmark releases, while ColBERT models frequently outperform much larger LLMs and rival specialized, larger models.
More from Research
- 25 LLM Foundation Interview Questions: From Tokens to Scaling Laws — techNmak · 2026-08-16
- New Agent Combines LLMs and Bayesian Inference for Efficient Scientific Discovery — burkov · 2026-08-16
- Google open-sources compiler for homomorphic encryption, enabling AI inference on encrypted data — DynamicWebPaige · 2026-08-16
- Neuroscientist: dendrites process info independently, brain power underestimated — JosephJacks_ · 2026-08-16
- Paper: Midtraining Bridges Pretraining and Posttraining Distributions — XiongChenyan · 2026-08-16
- Dev achieves real-time hybrid rendering of voxels, Gaussians and SDFs — anselm · 2026-08-16