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
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
Retrieval systems must prioritize utility for LLM generation quality over traditional relevance metrics, supported by a unified framework distinguishing LLM-agnostic vs specific and context-independent vs dependent utility.
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%.
-
AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
-
Beyond Relevance: Utility-Centric Retrieval in the LLM Era
Retrieval systems must prioritize utility for LLM generation quality over traditional relevance metrics, supported by a unified framework distinguishing LLM-agnostic vs specific and context-independent vs dependent utility.