Public Collection • 4 PapersUpdated Jan 3, 2026

Killer RAG

Curated by Ihab Tag

1

About this collection

Combine these methods for a superior RAG system: implement LUFY for long-term memory based on psychological importance like arousal, and CoopRAG to handle uncertainty and rerank using layer contrasts. Add Reasoning-Trace RAG to resolve conflicts via explicit logic traces and adjudication, then deploy HiFi-RAG for efficient hierarchical content filtering. Together, they create robust, conflict-aware, and psychologically grounded applications.

Papers in this collection

Dec 17, 2025Score: 14

Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers

Computation and Language

Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downsi...

Dec 27, 2025Score: 14

HiFi-RAG: Hierarchical Content Filtering and Two-Pass Generation for Open-Domain RAG

Computation and Language

Retrieval-Augmented Generation (RAG) in open-domain settings faces significant challenges regarding irrelevant information in retrieved documents and the alignment of generated answers with user inten...

Dec 18, 2025Score: 16

From Facts to Conclusions : Integrating Deductive Reasoning in Retrieval-Augmented LLMs

Computation and Language

Retrieval-Augmented Generation (RAG) grounds large language models (LLMs) in external evidence, but fails when retrieved sources conflict or contain outdated or subjective information. Prior work addr...

Dec 18, 2025Score: 15

Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting

Computation and Language

While Retrieval-Augmented Generation (RAG) has shown promise in enhancing long-term conversations, the increasing memory load as conversations progress degrades retrieval accuracy. Drawing on psycholo...

Create your own curated collections

Join AI Papers to curate your own research collections, get daily paper recommendations, and never miss an important breakthrough in AI research.

14-day free trial
No credit card required
Daily AI paper analysis