Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pal, Anwesan, Hovsepian, Karen, Guo, Tinghao, Zhao, Mengnan, Tripathi, Somendra, Kanakaris, Nikos, Mihaila, George, Nigam, Sumit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909870823833600
author Pal, Anwesan
Hovsepian, Karen
Guo, Tinghao
Zhao, Mengnan
Tripathi, Somendra
Kanakaris, Nikos
Mihaila, George
Nigam, Sumit
author_facet Pal, Anwesan
Hovsepian, Karen
Guo, Tinghao
Zhao, Mengnan
Tripathi, Somendra
Kanakaris, Nikos
Mihaila, George
Nigam, Sumit
contents Recent investigations into effective context lengths of modern flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models. While approaches like retrieval-augmented generation (RAG) and chunk-based re-ranking attempt to mitigate this issue, they are sensitive to chunking, embedding and retrieval strategies and models, and furthermore, rely on extensive pre-processing, knowledge acquisition and indexing steps. In this paper, we propose Tagging-Augmented Generation (TAG), a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios, without degrading and altering the integrity and composition of retrieved documents. We validate our hypothesis by augmenting two challenging and directly relevant question-answering benchmarks -- NoLima and NovelQA -- and show that tagging the context or even just adding tag definitions into QA prompts leads to consistent performance gains over the baseline -- up to 17% for 32K token contexts, and 2.9% in complex reasoning question-answering for multi-hop queries requiring knowledge across a wide span of text. Additional details are available at https://sites.google.com/view/tag-emnlp.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22956
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts
Pal, Anwesan
Hovsepian, Karen
Guo, Tinghao
Zhao, Mengnan
Tripathi, Somendra
Kanakaris, Nikos
Mihaila, George
Nigam, Sumit
Computation and Language
Information Retrieval
Recent investigations into effective context lengths of modern flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models. While approaches like retrieval-augmented generation (RAG) and chunk-based re-ranking attempt to mitigate this issue, they are sensitive to chunking, embedding and retrieval strategies and models, and furthermore, rely on extensive pre-processing, knowledge acquisition and indexing steps. In this paper, we propose Tagging-Augmented Generation (TAG), a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios, without degrading and altering the integrity and composition of retrieved documents. We validate our hypothesis by augmenting two challenging and directly relevant question-answering benchmarks -- NoLima and NovelQA -- and show that tagging the context or even just adding tag definitions into QA prompts leads to consistent performance gains over the baseline -- up to 17% for 32K token contexts, and 2.9% in complex reasoning question-answering for multi-hop queries requiring knowledge across a wide span of text. Additional details are available at https://sites.google.com/view/tag-emnlp.
title Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2510.22956