@inproceedings{bystronski-etal-2026-continuous,
title = "Continuous Context Sampling Allows Extending Diversity Boundaries of Large Language Models",
author = "Bystro{\'n}ski, Mateusz and
Han, Doheon and
Chawla, Nitesh V. and
Kajdanowicz, Tomasz Jan",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.126/",
pages = "1436--1450",
ISBN = "979-8-89176-393-7",
abstract = "Starting from the observation that conditioning a poetry-writing prompt with a pancake recipe leads an LLM to produce a coherent poem incorporating pancake-related content and, more broadly, that such contexts arrange themselves into a structured semantic vector space, we argue that this renders the space explorable. By sampling it and using the resulting continuous representations to condition an LLM{'}s generation distribution, we can systematically expand the model{'}s reachable semantic range.We introduce a framework that requires no modification of LLM parameters and operationalizes this idea by constructing a conditioning distribution from a small set of diverse anchor generations. This distribution conditions LLM{'}s generation via an xRAG-style projector.Our experiments demonstrate that this manifold-based conditioning substantially increases generative diversity, with direct benefits for enhancing divergent thinking, a core facet of creativity, in language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bystronski-etal-2026-continuous">
<titleInfo>
<title>Continuous Context Sampling Allows Extending Diversity Boundaries of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Bystroński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doheon</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitesh</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Chawla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="given">Jan</namePart>
<namePart type="family">Kajdanowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>Starting from the observation that conditioning a poetry-writing prompt with a pancake recipe leads an LLM to produce a coherent poem incorporating pancake-related content and, more broadly, that such contexts arrange themselves into a structured semantic vector space, we argue that this renders the space explorable. By sampling it and using the resulting continuous representations to condition an LLM’s generation distribution, we can systematically expand the model’s reachable semantic range.We introduce a framework that requires no modification of LLM parameters and operationalizes this idea by constructing a conditioning distribution from a small set of diverse anchor generations. This distribution conditions LLM’s generation via an xRAG-style projector.Our experiments demonstrate that this manifold-based conditioning substantially increases generative diversity, with direct benefits for enhancing divergent thinking, a core facet of creativity, in language models.</abstract>
<identifier type="citekey">bystronski-etal-2026-continuous</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.126/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1436</start>
<end>1450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Continuous Context Sampling Allows Extending Diversity Boundaries of Large Language Models
%A Bystroński, Mateusz
%A Han, Doheon
%A Chawla, Nitesh V.
%A Kajdanowicz, Tomasz Jan
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F bystronski-etal-2026-continuous
%X Starting from the observation that conditioning a poetry-writing prompt with a pancake recipe leads an LLM to produce a coherent poem incorporating pancake-related content and, more broadly, that such contexts arrange themselves into a structured semantic vector space, we argue that this renders the space explorable. By sampling it and using the resulting continuous representations to condition an LLM’s generation distribution, we can systematically expand the model’s reachable semantic range.We introduce a framework that requires no modification of LLM parameters and operationalizes this idea by constructing a conditioning distribution from a small set of diverse anchor generations. This distribution conditions LLM’s generation via an xRAG-style projector.Our experiments demonstrate that this manifold-based conditioning substantially increases generative diversity, with direct benefits for enhancing divergent thinking, a core facet of creativity, in language models.
%U https://aclanthology.org/2026.acl-srw.126/
%P 1436-1450
Markdown (Informal)
[Continuous Context Sampling Allows Extending Diversity Boundaries of Large Language Models](https://aclanthology.org/2026.acl-srw.126/) (Bystroński et al., ACL 2026)
ACL