@inproceedings{partalidou-etal-2026-pixels,
title = "From Pixels to Tokens: Adaptive {LLM} Decoding and Reliability Analysis with Otsu Thresholding",
author = "Partalidou, Eleni and
Passali, Tatiana and
Zerva, Chrysoula and
Tsoumakas, Grigorios and
Ananiadou, Sophia",
editor = {Aziz, Wilker and
Berant, Jonathan and
Eikema, Bryan and
Ilia, Evgenia and
de Marneffe, Marie-Catherine and
Plank, Barbara and
Shelmanov, Artem and
Swayamdipta, Swabha and
Tiedemann, J{\"o}rg and
Vazhentsev, Artem and
V{\'a}zquez, Ra{\'u}l and
Zerva, Chrysoula},
booktitle = "The Proceedings of the Third Workshop on Uncertainty-Aware {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.uncertainlp-main.32/",
pages = "518--543",
ISBN = "979-8-89176-486-6",
abstract = "This paper investigates the relationship between generation-time uncertainty and output reliability in probabilistic Large Language Model (LLM) decoding. Specifically, we assess the correlation between several factuality, quality and certainty metrics to infer existing patterns across state-of-the-art decoding strategies, diverse tasks and instruction-tuned models. We also propose a novel, image processing-inspired decoding approach, Otsu Thresholding, that performs adaptive, parameter-free threshold selection directly from the next-token predictive confidence distribution. The proposed Otsu-based variants achieve competitive quality and factuality across tasks and models, while exhibiting concentrated predictive distributions comparable to strong truncation-based baselines. Furthermore, we employ a selective filtering setup to analyze the impact of removing highly uncertain instances on the quality and factuality metrics, ultimately revealing that filtering based on averaged token-level uncertainty metrics can be practically useful for identifying less reliable generations, with filtering frequently improving the quality or factuality of the retained outputs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="partalidou-etal-2026-pixels">
<titleInfo>
<title>From Pixels to Tokens: Adaptive LLM Decoding and Reliability Analysis with Otsu Thresholding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleni</namePart>
<namePart type="family">Partalidou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Passali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigorios</namePart>
<namePart type="family">Tsoumakas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</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>The Proceedings of the Third Workshop on Uncertainty-Aware NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Eikema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Ilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Vazhentsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</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">979-8-89176-486-6</identifier>
</relatedItem>
<abstract>This paper investigates the relationship between generation-time uncertainty and output reliability in probabilistic Large Language Model (LLM) decoding. Specifically, we assess the correlation between several factuality, quality and certainty metrics to infer existing patterns across state-of-the-art decoding strategies, diverse tasks and instruction-tuned models. We also propose a novel, image processing-inspired decoding approach, Otsu Thresholding, that performs adaptive, parameter-free threshold selection directly from the next-token predictive confidence distribution. The proposed Otsu-based variants achieve competitive quality and factuality across tasks and models, while exhibiting concentrated predictive distributions comparable to strong truncation-based baselines. Furthermore, we employ a selective filtering setup to analyze the impact of removing highly uncertain instances on the quality and factuality metrics, ultimately revealing that filtering based on averaged token-level uncertainty metrics can be practically useful for identifying less reliable generations, with filtering frequently improving the quality or factuality of the retained outputs.</abstract>
<identifier type="citekey">partalidou-etal-2026-pixels</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.32/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>518</start>
<end>543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Pixels to Tokens: Adaptive LLM Decoding and Reliability Analysis with Otsu Thresholding
%A Partalidou, Eleni
%A Passali, Tatiana
%A Zerva, Chrysoula
%A Tsoumakas, Grigorios
%A Ananiadou, Sophia
%Y Aziz, Wilker
%Y Berant, Jonathan
%Y Eikema, Bryan
%Y Ilia, Evgenia
%Y de Marneffe, Marie-Catherine
%Y Plank, Barbara
%Y Shelmanov, Artem
%Y Swayamdipta, Swabha
%Y Tiedemann, Jörg
%Y Vazhentsev, Artem
%Y Vázquez, Raúl
%Y Zerva, Chrysoula
%S The Proceedings of the Third Workshop on Uncertainty-Aware NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-486-6
%F partalidou-etal-2026-pixels
%X This paper investigates the relationship between generation-time uncertainty and output reliability in probabilistic Large Language Model (LLM) decoding. Specifically, we assess the correlation between several factuality, quality and certainty metrics to infer existing patterns across state-of-the-art decoding strategies, diverse tasks and instruction-tuned models. We also propose a novel, image processing-inspired decoding approach, Otsu Thresholding, that performs adaptive, parameter-free threshold selection directly from the next-token predictive confidence distribution. The proposed Otsu-based variants achieve competitive quality and factuality across tasks and models, while exhibiting concentrated predictive distributions comparable to strong truncation-based baselines. Furthermore, we employ a selective filtering setup to analyze the impact of removing highly uncertain instances on the quality and factuality metrics, ultimately revealing that filtering based on averaged token-level uncertainty metrics can be practically useful for identifying less reliable generations, with filtering frequently improving the quality or factuality of the retained outputs.
%U https://aclanthology.org/2026.uncertainlp-main.32/
%P 518-543
Markdown (Informal)
[From Pixels to Tokens: Adaptive LLM Decoding and Reliability Analysis with Otsu Thresholding](https://aclanthology.org/2026.uncertainlp-main.32/) (Partalidou et al., UncertaiNLP 2026)
ACL