@inproceedings{robinette-etal-2026-repeatedly,
title = "We Are What We Repeatedly Do: Improving Long Context Instruction Following",
author = "Robinette, Preston K and
Hard, Andrew and
Ramaswamy, Swaroop and
Amid, Ehsan and
Mathews, Rajiv and
Johnson, Taylor T",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.254/",
pages = "4855--4884",
ISBN = "979-8-89176-386-9",
abstract = "Large language model context lengths have grown rapidly in recent years, from 512 tokens in GPT to 2M tokens in Gemini 1.5 Pro. Larger context windows enable models to condition on significantly more input tokens, leading to higher quality responses for some user prompts. However, longer contexts also pose challenges to system instruction adherence. In this work, we formalize verifiable instructions to evaluate model *compliance* based on clear, measurable criteria. From this criteria, we present **VerIFY**, a **Ver**ifiable **I**nstruction **F**ollowing **Y**ardstick dataset designed to benchmark the compliance and accuracy of LLMs in adhering to various types of instructions across multi-turn, long-context conversations. From experiments with open-source models, we reveal insights into instruction-following failures in long contexts, helping to improve the reliability, safety, and precision of these models. Furthermore, we implement and evaluate six mitigation strategies to enhance instruction compliance in extended contexts, achieving an improvement up to 79{\%}. This is the first work to consider instruction following for multi-turn, long context conversations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="robinette-etal-2026-repeatedly">
<titleInfo>
<title>We Are What We Repeatedly Do: Improving Long Context Instruction Following</title>
</titleInfo>
<name type="personal">
<namePart type="given">Preston</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Robinette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Hard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swaroop</namePart>
<namePart type="family">Ramaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Amid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajiv</namePart>
<namePart type="family">Mathews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taylor</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Large language model context lengths have grown rapidly in recent years, from 512 tokens in GPT to 2M tokens in Gemini 1.5 Pro. Larger context windows enable models to condition on significantly more input tokens, leading to higher quality responses for some user prompts. However, longer contexts also pose challenges to system instruction adherence. In this work, we formalize verifiable instructions to evaluate model *compliance* based on clear, measurable criteria. From this criteria, we present **VerIFY**, a **Ver**ifiable **I**nstruction **F**ollowing **Y**ardstick dataset designed to benchmark the compliance and accuracy of LLMs in adhering to various types of instructions across multi-turn, long-context conversations. From experiments with open-source models, we reveal insights into instruction-following failures in long contexts, helping to improve the reliability, safety, and precision of these models. Furthermore, we implement and evaluate six mitigation strategies to enhance instruction compliance in extended contexts, achieving an improvement up to 79%. This is the first work to consider instruction following for multi-turn, long context conversations.</abstract>
<identifier type="citekey">robinette-etal-2026-repeatedly</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.254/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4855</start>
<end>4884</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T We Are What We Repeatedly Do: Improving Long Context Instruction Following
%A Robinette, Preston K.
%A Hard, Andrew
%A Ramaswamy, Swaroop
%A Amid, Ehsan
%A Mathews, Rajiv
%A Johnson, Taylor T.
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F robinette-etal-2026-repeatedly
%X Large language model context lengths have grown rapidly in recent years, from 512 tokens in GPT to 2M tokens in Gemini 1.5 Pro. Larger context windows enable models to condition on significantly more input tokens, leading to higher quality responses for some user prompts. However, longer contexts also pose challenges to system instruction adherence. In this work, we formalize verifiable instructions to evaluate model *compliance* based on clear, measurable criteria. From this criteria, we present **VerIFY**, a **Ver**ifiable **I**nstruction **F**ollowing **Y**ardstick dataset designed to benchmark the compliance and accuracy of LLMs in adhering to various types of instructions across multi-turn, long-context conversations. From experiments with open-source models, we reveal insights into instruction-following failures in long contexts, helping to improve the reliability, safety, and precision of these models. Furthermore, we implement and evaluate six mitigation strategies to enhance instruction compliance in extended contexts, achieving an improvement up to 79%. This is the first work to consider instruction following for multi-turn, long context conversations.
%U https://aclanthology.org/2026.findings-eacl.254/
%P 4855-4884
Markdown (Informal)
[We Are What We Repeatedly Do: Improving Long Context Instruction Following](https://aclanthology.org/2026.findings-eacl.254/) (Robinette et al., Findings 2026)
ACL