@inproceedings{lopez-etal-2026-safe,
title = "Safe Adaptive Context and {TACER}: Task-Aware Evidence Routing for Token-Efficient Retrieval-Augmented Generation",
author = "Lopez, Joel Vazquez and
Alexa, Andreia and
Auce, K{\={a}}rlis M{\={a}}rti{\c{n}}{\v{s}} and
Brudzewski, Simon Backhaus and
Ahmad, Sheraz",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.33/",
pages = "418--433",
ISBN = "979-8-89176-478-1",
abstract = "Retrieval-Augmented Generation (RAG) pipelines often pass a fixed number of retrieved documents to the generator, even though evidence needs vary by query. We study context selection as a post-retrieval control problem: given the same candidate list, how much evidence should enter the prompt, and in what form? We present Safe Adaptive Context, a lightweight controller that starts with limited evidence and expands when the generated answer appears weak, and TACER, a task-aware extension that routes between compact evidence and safer broader context using retrieval-side and evidence-coverage signals. Across five datasets, two generators, and stronger retriever settings, the controllers substantially reduce provider-reported token use while preserving most Fixed Top-10 answer quality. In a five-dataset, 500-query external-baseline stress test, Safe Adaptive Context retains 99.8{\%} of Fixed Top-10 F1 with 55.0{\%} token reduction, while TACER retains 99.4{\%} with 60.4{\%} token reduction. The contribution is not universal quality improvement, but practical quality-preserving efficiency through task-aware context control."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lopez-etal-2026-safe">
<titleInfo>
<title>Safe Adaptive Context and TACER: Task-Aware Evidence Routing for Token-Efficient Retrieval-Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="given">Vazquez</namePart>
<namePart type="family">Lopez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreia</namePart>
<namePart type="family">Alexa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kārlis</namePart>
<namePart type="given">Mārtiņš</namePart>
<namePart type="family">Auce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="given">Backhaus</namePart>
<namePart type="family">Brudzewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheraz</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) pipelines often pass a fixed number of retrieved documents to the generator, even though evidence needs vary by query. We study context selection as a post-retrieval control problem: given the same candidate list, how much evidence should enter the prompt, and in what form? We present Safe Adaptive Context, a lightweight controller that starts with limited evidence and expands when the generated answer appears weak, and TACER, a task-aware extension that routes between compact evidence and safer broader context using retrieval-side and evidence-coverage signals. Across five datasets, two generators, and stronger retriever settings, the controllers substantially reduce provider-reported token use while preserving most Fixed Top-10 answer quality. In a five-dataset, 500-query external-baseline stress test, Safe Adaptive Context retains 99.8% of Fixed Top-10 F1 with 55.0% token reduction, while TACER retains 99.4% with 60.4% token reduction. The contribution is not universal quality improvement, but practical quality-preserving efficiency through task-aware context control.</abstract>
<identifier type="citekey">lopez-etal-2026-safe</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.33/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>418</start>
<end>433</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Safe Adaptive Context and TACER: Task-Aware Evidence Routing for Token-Efficient Retrieval-Augmented Generation
%A Lopez, Joel Vazquez
%A Alexa, Andreia
%A Auce, Kārlis Mārtiņš
%A Brudzewski, Simon Backhaus
%A Ahmad, Sheraz
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F lopez-etal-2026-safe
%X Retrieval-Augmented Generation (RAG) pipelines often pass a fixed number of retrieved documents to the generator, even though evidence needs vary by query. We study context selection as a post-retrieval control problem: given the same candidate list, how much evidence should enter the prompt, and in what form? We present Safe Adaptive Context, a lightweight controller that starts with limited evidence and expands when the generated answer appears weak, and TACER, a task-aware extension that routes between compact evidence and safer broader context using retrieval-side and evidence-coverage signals. Across five datasets, two generators, and stronger retriever settings, the controllers substantially reduce provider-reported token use while preserving most Fixed Top-10 answer quality. In a five-dataset, 500-query external-baseline stress test, Safe Adaptive Context retains 99.8% of Fixed Top-10 F1 with 55.0% token reduction, while TACER retains 99.4% with 60.4% token reduction. The contribution is not universal quality improvement, but practical quality-preserving efficiency through task-aware context control.
%U https://aclanthology.org/2026.groundlm-1.33/
%P 418-433
Markdown (Informal)
[Safe Adaptive Context and TACER: Task-Aware Evidence Routing for Token-Efficient Retrieval-Augmented Generation](https://aclanthology.org/2026.groundlm-1.33/) (Lopez et al., GroundLM 2026)
ACL