X-SYNTH synthesizes enterprise context from digital human attention using Digital Twin Signatures and seven attention filters, raising true lead rate from 9.5% to 61.9% while cutting false lead rate to 18.8%.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ReaLM-Retrieve uses step-level uncertainty to trigger retrievals during reasoning, achieving 10.1% better F1 scores and 47% fewer calls on multi-hop QA benchmarks.
CHR improves medical QA retrieval by generating a target hypothesis H+ and a mimic hypothesis H-, then scoring documents by cosine similarity to H+ minus cosine similarity to H-, beating five RAG baselines on three benchmarks.
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
A train-free phrase memory system for LLMs uses SSD-backed hierarchical storage and early-exit predictive prefetching to improve downstream accuracy without backbone training.
Ex2Bundle synthesizes package queries from example bundles using aggregate constraints and applies data-aware relaxation when constraints are infeasible, shown on focused text snippet extraction.
citing papers explorer
-
X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention
X-SYNTH synthesizes enterprise context from digital human attention using Digital Twin Signatures and seven attention filters, raising true lead rate from 9.5% to 61.9% while cutting false lead rate to 18.8%.
-
When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
ReaLM-Retrieve uses step-level uncertainty to trigger retrievals during reasoning, achieving 10.1% better F1 scores and 47% fewer calls on multi-hop QA benchmarks.
-
Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answering
CHR improves medical QA retrieval by generating a target hypothesis H+ and a mimic hypothesis H-, then scoring documents by cosine similarity to H+ minus cosine similarity to H-, beating five RAG baselines on three benchmarks.
-
Retrieval-Augmented Generation for Natural Language Processing: A Survey
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
-
TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
A train-free phrase memory system for LLMs uses SSD-backed hierarchical storage and early-exit predictive prefetching to improve downstream accuracy without backbone training.
-
Example-Driven Intent Synthesis for Constrained Data Bundle Retrieval: Focused Text Snippet Extraction and Beyond
Ex2Bundle synthesizes package queries from example bundles using aggregate constraints and applies data-aware relaxation when constraints are infeasible, shown on focused text snippet extraction.