mlsanityData to 14 Oct 2026

The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search

arXiv 2608.23252 ↗First posted 24 Aug 2026cs.LG cs.CL cs.IRcited by 0

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

Abstract (arXiv)

As Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of evidence utilization, and suboptimal context budget allocation. We resolve both sequentially. To resolve measurement, we expose a pervasive ``diagnostic illusion'': standard relevance proxies fail catastrophically on hard negatives. We replace them with an efficient causal leave-one-out probe that accurately isolates generative reliance and formally calibrates the structural dilution of LLM attention. To resolve allocation, we deploy this causal probe in a deconfounded factorial grid. We prove that the prevailing strategy of monolithic context widening is an architectural trap penalized by relevance decay. Instead, allocating compute iteratively across multiple sequential generations drives transformative portfolio recall gains of 16.7--20.5 absolute percentage points, scaling robustly up to 32B models. Finally, we unify these solutions into a deployable closed-loop submodular scheduler. Augmented by an attribution-steered contrastive decoder to override LLM attention inertia, our architecture systematically forces fresh evidence integration. By dominating classical open-loop baselines, we establish sequential, feedback-driven orchestration as the definitive paradigm for generative search. Our code, data, and causal measurement instruments are available at https://github.com/PeiYangLiu/ascp.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 85 of its 126 references that are in the map. First posted on arXiv 24 Aug 2026.

Builds on

85 of 126 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs16 Feb
  2. 2024Inference Scaling for Bridging Retrieval and Augmented Generation14 Dec
  3. 2024In Defense of RAG in the Era of Long-Context Language Models3 Sep
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 81

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2020Scaling Laws for Neural Language Modelscited by 6,586
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  9. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  12. 2017Axiomatic Attribution for Deep Networkscited by 3,384
38 more
  1. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  2. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  3. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  5. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  7. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  9. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  10. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  11. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  12. 2018Hierarchical Neural Story Generationcited by 1,193
  13. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  14. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  15. 2019Attention is not Explanationcited by 929
  16. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  17. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  18. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  19. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  20. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  21. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  22. 2019Attention is not not Explanationcited by 636
  23. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  24. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  25. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  26. 2019ELI5: Long Form Question Answeringcited by 575
  27. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  28. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 491
  29. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  30. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  31. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  32. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  33. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  34. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  35. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 311
  36. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  37. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  38. 2022Teaching language models to support answers with verified quotescited by 292

50 most cited of 81 All 81 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Retrieval from Within: An Intrinsic Capability of Attention-Based Models
  2. 2026BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
  3. 2026From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism
  4. 2026Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
  5. 2026The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation
  6. 2026In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
  7. 2026The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content
  8. 2025Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation