@inproceedings{papucci-etal-2026-lexical,
title = "Lexical Conditioning of Model{'}s Distribution through Uncertainty-gated Soft-Mixing of Probabilities",
author = "Papucci, Michele and
Venturi, Giulia and
Dell{'}Orletta, Felice",
editor = "Shardlow, Matthew and
Fran{\c{c}}ois, Thomas and
Amaro, Raquel and
Baptista, Jorge and
Cardon, R{\'e}mi and
Ribeiro, Eug{\'e}nio and
Saggion, Horacio and
Stodden, Regina and
Todirascu, Amalia and
Wilkens, Rodrigo",
booktitle = "Proceedings of the Joint Workshop on Readability and Text Simplification ({READI}x{TSAR}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.readi-1.7/",
doi = "10.63317/5hgiz64xsj6s",
pages = "89--100",
abstract = "We present Uncertainty-Gated Lexical Decoding (UGLD), a decoding-time framework for fine-grained lexical control in Large Language Models (LLMs) that explicitly addresses the trade-off between controllability and fluency. UGLD adaptively scales intervention through an entropy-based gating mechanism derived from the model{'}s predictive distribution, activating control when uncertainty is high and limiting interference when predictions are confident. The method supports both promotion toward and against predefined vocabularies. We evaluate UGLD in Italian on two open-weight LLMs (ANITA 8B and Qwen 3 4B) across paraphrasing and free-text generation settings, considering Simple Vocabulary Conditioning and Jargon Reduction scenarios. Automatic evaluation shows consistent improvements in lexical coverage over standard decoding strategies, while human evaluation confirms that fluency is preserved under controlled intervention."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papucci-etal-2026-lexical">
<titleInfo>
<title>Lexical Conditioning of Model’s Distribution through Uncertainty-gated Soft-Mixing of Probabilities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Papucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Venturi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Amaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Baptista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amalia</namePart>
<namePart type="family">Todirascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Wilkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Uncertainty-Gated Lexical Decoding (UGLD), a decoding-time framework for fine-grained lexical control in Large Language Models (LLMs) that explicitly addresses the trade-off between controllability and fluency. UGLD adaptively scales intervention through an entropy-based gating mechanism derived from the model’s predictive distribution, activating control when uncertainty is high and limiting interference when predictions are confident. The method supports both promotion toward and against predefined vocabularies. We evaluate UGLD in Italian on two open-weight LLMs (ANITA 8B and Qwen 3 4B) across paraphrasing and free-text generation settings, considering Simple Vocabulary Conditioning and Jargon Reduction scenarios. Automatic evaluation shows consistent improvements in lexical coverage over standard decoding strategies, while human evaluation confirms that fluency is preserved under controlled intervention.</abstract>
<identifier type="citekey">papucci-etal-2026-lexical</identifier>
<identifier type="doi">10.63317/5hgiz64xsj6s</identifier>
<location>
<url>https://aclanthology.org/2026.readi-1.7/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>89</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexical Conditioning of Model’s Distribution through Uncertainty-gated Soft-Mixing of Probabilities
%A Papucci, Michele
%A Venturi, Giulia
%A Dell’Orletta, Felice
%Y Shardlow, Matthew
%Y François, Thomas
%Y Amaro, Raquel
%Y Baptista, Jorge
%Y Cardon, Rémi
%Y Ribeiro, Eugénio
%Y Saggion, Horacio
%Y Stodden, Regina
%Y Todirascu, Amalia
%Y Wilkens, Rodrigo
%S Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F papucci-etal-2026-lexical
%X We present Uncertainty-Gated Lexical Decoding (UGLD), a decoding-time framework for fine-grained lexical control in Large Language Models (LLMs) that explicitly addresses the trade-off between controllability and fluency. UGLD adaptively scales intervention through an entropy-based gating mechanism derived from the model’s predictive distribution, activating control when uncertainty is high and limiting interference when predictions are confident. The method supports both promotion toward and against predefined vocabularies. We evaluate UGLD in Italian on two open-weight LLMs (ANITA 8B and Qwen 3 4B) across paraphrasing and free-text generation settings, considering Simple Vocabulary Conditioning and Jargon Reduction scenarios. Automatic evaluation shows consistent improvements in lexical coverage over standard decoding strategies, while human evaluation confirms that fluency is preserved under controlled intervention.
%R 10.63317/5hgiz64xsj6s
%U https://aclanthology.org/2026.readi-1.7/
%U https://doi.org/10.63317/5hgiz64xsj6s
%P 89-100
Markdown (Informal)
[Lexical Conditioning of Model’s Distribution through Uncertainty-gated Soft-Mixing of Probabilities](https://aclanthology.org/2026.readi-1.7/) (Papucci et al., READI-TSAR 2026)
ACL