mlsanityData to 14 Oct 2026

The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems

arXiv 2606.28327 ↗First posted 9 May 2026cs.IR cs.AI cs.CLcited by 0

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

Abstract (arXiv)

How do retrieval bounds compare between human episodic memory and Retrieval-Augmented Generation (RAG) systems under semantic interference? We present a unified signal detection theory (SDT) framework that applies to both, and use it to fit behavioral and computational data in matched paradigms. Both systems show logarithmic accuracy decline with association count (fan), but humans exhibit lower interference sensitivity (α/σ = 0.41) than dense passage retrieval (α/σ = 0.67), with cognitively-inspired HippoRAG falling between the two (α/σ = 0.44). Behavioral experiments (N = 112) and simulations validate the framework; parameter recovery confirms identifiability (r ≥ .93) and model comparison favors the logarithmic specification over a power-law alternative (DeltaBIC > 15). We discuss encoding specificity, temporal context binding, and retrieval gating as candidate mechanisms whose causal role remains to be established. Six falsifiable predictions connect cognitive memory research with AI retrieval evaluation.

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 10 of its 41 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

10 of 41 references.

References · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  5. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  6. 2022Using cognitive psychology to understand GPT-3cited by 398
  7. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  8. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  9. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  10. 2023Attention Sorting Combats Recency Bias In Long Context Language Modelscited by 90

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs
  2. 2026Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models
  3. 2026Separating Semantic Competition from Context Length in RAG Reading
  4. 2026Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction
  5. 2026The RAT: A Unified Bayesian Model for RAG Evaluation
  6. 2026Quantifying Prior Dominance in RAG Systems
  7. 2024Human-inspired Episodic Memory for Infinite Context LLMs
  8. 2026FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG