LPES uses per-layer scaling factors optimized by a genetic algorithm with Bézier curves to balance attention and improve long-context LLM performance by up to 11.2% on key-value retrieval.
arXiv preprint arXiv:2407.01219 , year=
7 Pith papers cite this work, alongside 6 external citations. Polarity classification is still indexing.
7
Pith papers citing it
6
external citations · external index
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
method 1polarities
use method 1representative citing papers
Poisoning external knowledge bases with LLM-agent-crafted documents can increase RAG inference token consumption by up to 13.12 times at over 90% success rate while preserving answer quality.
A taxonomy-guided RAG system with LLMs reduces hallucinations and improves migration suggestions for Qiskit code compared to unconstrained retrieval.
Grep retrieval generally outperforms vector retrieval in agentic search tasks, with performance varying strongly by agent harness and tool-calling style.
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
RAG-DIVE uses an LLM to dynamically generate, validate, and evaluate multi-turn dialogues for assessing RAG system performance in interactive settings.
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.
citing papers explorer
-
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling
LPES uses per-layer scaling factors optimized by a genetic algorithm with Bézier curves to balance attention and improve long-context LLM performance by up to 11.2% on key-value retrieval.
-
Inference Cost Attacks for Retrieval-Augmented Large Language Models
Poisoning external knowledge bases with LLM-agent-crafted documents can increase RAG inference token consumption by up to 13.12 times at over 90% success rate while preserving answer quality.
-
Qiskit Code Migration with LLMs
A taxonomy-guided RAG system with LLMs reduces hallucinations and improves migration suggestions for Qiskit code compared to unconstrained retrieval.
-
Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
Grep retrieval generally outperforms vector retrieval in agentic search tasks, with performance varying strongly by agent harness and tool-calling style.
-
Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
-
RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation
RAG-DIVE uses an LLM to dynamically generate, validate, and evaluate multi-turn dialogues for assessing RAG system performance in interactive settings.
-
A Survey on Retrieval-Augmented Text Generation for Large Language Models
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.