NEST: Nested Evidence Survival for Retrieval

Akshay Verma, Siddharth Pillai, Prateek Sircar, Deepak Gupta

Keywords: RAG, Information Retrieval, Low Latency Systems

TL;DR: We propose NEst - framework improves recall by using Nested Evidence Survival, which defers pruning under nested retrieval contexts. The key findings show NEST outperforms baselines in EM, F1, and recall, while maintaining low latency.

Abstract: Retrieval-Augmented Generation (RAG) systems degrade sharply under extreme noise, where relevant evidence is sparse and easily pruned by static retrieval decisions. Existing approaches fixed top-k retrieval, hierarchical chunking, cross-encoder reranking, or policy-based iterative control- either rely on rigid heuristics or incur substantial computational overhead, and often fail to recover context-dependent evidence without introducing redundancy or latency. We introduce NEST (Nested Evidence Survival for Retrieval), a lightweight, training-free RAG framework that improves factual grounding by explicitly separating recall amplification from precision selection. NEST first maximizes recall through Nested Evidence Survival, evaluating candidates under nested retrieval contexts to rescue evidence that would otherwise be pruned by static chunking. It then applies a survival-consistent Mean Reciprocal Rank (MRR) selection mechanism to retain evidence that remains salient across retrieval scopes, removing redundancy without harming recall. Evaluated on WebQuestions, HotpotQA (distractor setting), and a proprietary InternalQA benchmark with 50M Common Crawl distractors, NEST consistently outperforms strong adaptive RAG baselines, including DeepRAG, improving EM by up to +2.4 pp and F1 by +2.1 pp, while increasing retrieval recall by +6.8 pp. These gains are achieved with only 12–18 ms additional latency. Ablation studies confirm that Nested Evidence Survival drives recall improvements, while MRR-based selection converts these gains into precision, demonstrating that recall-first retrieval with principled pruning can outperform iterative control and model scaling in retrieval-augmented generation.

Submission Type: Deployed

Submission Number: 118