Saved in:
Bibliographic Details
Main Authors: Taguchi, Chihiro, Maekawa, Seiji, Bhutani, Nikita
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.08479
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915523598483456
author Taguchi, Chihiro
Maekawa, Seiji
Bhutani, Nikita
author_facet Taguchi, Chihiro
Maekawa, Seiji
Bhutani, Nikita
contents Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal external context to retrieve remains an open problem: fixing the retrieval size risks either wasting tokens or omitting key evidence. Existing adaptive methods like Self-RAG and Self-Route rely on iterative LLM prompting and perform well on factoid QA, but struggle with aggregation QA, where the optimal context size is both unknown and variable. We present Adaptive-$k$ retrieval, a simple and effective single-pass method that adaptively selects the number of passages based on the distribution of the similarity scores between the query and the candidate passages. It does not require model fine-tuning, extra LLM inferences or changes to existing retriever-reader pipelines. On both factoid and aggregation QA benchmarks, Adaptive-$k$ matches or outperforms fixed-$k$ baselines while using up to 10x fewer tokens than full-context input, yet still retrieves 70% of relevant passages. It improves accuracy across five LCLMs and two embedding models, highlighting that dynamically adjusting context size leads to more efficient and accurate QA.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08479
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-$k$
Taguchi, Chihiro
Maekawa, Seiji
Bhutani, Nikita
Computation and Language
Artificial Intelligence
Information Retrieval
Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal external context to retrieve remains an open problem: fixing the retrieval size risks either wasting tokens or omitting key evidence. Existing adaptive methods like Self-RAG and Self-Route rely on iterative LLM prompting and perform well on factoid QA, but struggle with aggregation QA, where the optimal context size is both unknown and variable. We present Adaptive-$k$ retrieval, a simple and effective single-pass method that adaptively selects the number of passages based on the distribution of the similarity scores between the query and the candidate passages. It does not require model fine-tuning, extra LLM inferences or changes to existing retriever-reader pipelines. On both factoid and aggregation QA benchmarks, Adaptive-$k$ matches or outperforms fixed-$k$ baselines while using up to 10x fewer tokens than full-context input, yet still retrieves 70% of relevant passages. It improves accuracy across five LCLMs and two embedding models, highlighting that dynamically adjusting context size leads to more efficient and accurate QA.
title Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-$k$
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2506.08479