← all papers · overview

From Artificial Needles To Real Haystacks: Improving Retrieval Capabilities In Llms By Finetuning On Synthetic Data

Abstract

Recent studies have shown that Large Language Models (LLMs) struggle to accurately retrieve information and maintain reasoning capabilities when processing long-context inputs. To address these limitations, we propose a finetuning approach utilizing a carefully designed synthetic dataset comprising numerical key-value retrieval tasks. Our experiments on models like GPT-3.5 Turbo and Mistral 7B dem

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).