mlsanityData to 7 Oct 2026

Candidate-Constrained Retrieval-Augmented Generation for LongEval-RAG: System Design and Empirical Analysis

arXiv 2607.04008 ↗First posted 4 Jul 2026cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

We present a candidate-constrained retrieval-augmented generation system for LongEval-RAG, where each query is associated with an organizer-provided candidate set and all retrieved evidence and final citations must remain within that set. The system combines deterministic provenance tracking with passage-based retrieval, deterministic query expansion, pseudo-relevance feedback (PRF), reciprocal rank fusion (RRF), lightweight evidence reranking, citation-aware evidence aggregation, and optional MiniLM sentence reranking. We evaluate ten pipeline variants using a primary organizer evaluation and a supplementary self-generated diagnostic protocol. The primary evaluation shows that the strongest balanced variant is rule-minilm: a rule-based chunking pipeline with query expansion, PRF, RRF, reranking, citation prior, and late MiniLM sentence selection. This variant obtains the highest BERTScore, retrieval precision, nugget coverage, and average grade among our submissions. The result suggests that the main gain does not come from more complex semantic or topic-shift chunking, but from pairing stable rule-based evidence units with sentence-level neural selection before generation. The supplementary LLM-judge evaluation remains useful for early diagnosis and additional analysis, but it emphasizes different systems than the primary gold-answer and nugget-based evaluation, highlighting the need for multi-metric RAG evaluation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 21 references that are in the map. First posted on arXiv 4 Jul 2026.

Builds on

9 of 21 references.

References · 9

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  6. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  7. 2019Passage Re-ranking with BERTcited by 629
  8. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  9. 2023Query2doc: Query Expansion with Large Language Modelscited by 146

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation
  2. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  3. 2026Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection
  4. 2026M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation
  5. 2026Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
  6. 2026A Hybrid Retrieval and Reranking Framework for Evidence-Grounded Retrieval-Augmented Generation
  7. 2026REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
  8. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers