@inproceedings{cohen-etal-2026-dfpe,
title = "{DFPE}: A Diverse Fingerprint Ensemble for Enhancing {LLM} Performance",
author = "Cohen, Seffi and
Inger, Nurit Cohen and
Goldshlager, Niv and
Shapira, Bracha and
Rokach, Lior",
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.282/",
pages = "5326--5336",
ISBN = "979-8-89176-386-9",
abstract = "Large Language Models (LLMs) demonstrate impressive capabilities but exhibit inconsistent performance across diverse domains. We propose DFPE (Diverse Fingerprint Ensemble), a novel training-free method that systematically constructs subject-adaptive ensembles by balancing model diversity and competence. DFPE introduces three key innovations: (1) semantic fingerprinting using averaged response embeddings to capture distinct problem-solving patterns, (2) DBSCAN-based clustering with quantile-based competence filtering to ensure diverse yet capable model selection, and (3) exponentially-weighted aggregation adapted to subject-specific performance. Our method{'}s effectiveness is highlighted on the challenging MMLU-pro benchmark, where DFPE achieves a striking 17.1 percentage point gain over the best single model, reaching 71.4{\%} accuracy. This strong performance is consistent across other standard benchmarks, with significant accuracy improvements of 4.4 points on AGIEval and 2.7 points on MMLU. Our results underscore that a systematic approach to ensemble construction - one that balances diversity, subject-specific competence, and adaptive weighting, can substantially enhance the generalization and robustness of LLMs on multifaceted language understanding tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cohen-etal-2026-dfpe">
<titleInfo>
<title>DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seffi</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nurit</namePart>
<namePart type="given">Cohen</namePart>
<namePart type="family">Inger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niv</namePart>
<namePart type="family">Goldshlager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bracha</namePart>
<namePart type="family">Shapira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lior</namePart>
<namePart type="family">Rokach</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 Models (LLMs) demonstrate impressive capabilities but exhibit inconsistent performance across diverse domains. We propose DFPE (Diverse Fingerprint Ensemble), a novel training-free method that systematically constructs subject-adaptive ensembles by balancing model diversity and competence. DFPE introduces three key innovations: (1) semantic fingerprinting using averaged response embeddings to capture distinct problem-solving patterns, (2) DBSCAN-based clustering with quantile-based competence filtering to ensure diverse yet capable model selection, and (3) exponentially-weighted aggregation adapted to subject-specific performance. Our method’s effectiveness is highlighted on the challenging MMLU-pro benchmark, where DFPE achieves a striking 17.1 percentage point gain over the best single model, reaching 71.4% accuracy. This strong performance is consistent across other standard benchmarks, with significant accuracy improvements of 4.4 points on AGIEval and 2.7 points on MMLU. Our results underscore that a systematic approach to ensemble construction - one that balances diversity, subject-specific competence, and adaptive weighting, can substantially enhance the generalization and robustness of LLMs on multifaceted language understanding tasks.</abstract>
<identifier type="citekey">cohen-etal-2026-dfpe</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.282/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>5326</start>
<end>5336</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance
%A Cohen, Seffi
%A Inger, Nurit Cohen
%A Goldshlager, Niv
%A Shapira, Bracha
%A Rokach, Lior
%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 cohen-etal-2026-dfpe
%X Large Language Models (LLMs) demonstrate impressive capabilities but exhibit inconsistent performance across diverse domains. We propose DFPE (Diverse Fingerprint Ensemble), a novel training-free method that systematically constructs subject-adaptive ensembles by balancing model diversity and competence. DFPE introduces three key innovations: (1) semantic fingerprinting using averaged response embeddings to capture distinct problem-solving patterns, (2) DBSCAN-based clustering with quantile-based competence filtering to ensure diverse yet capable model selection, and (3) exponentially-weighted aggregation adapted to subject-specific performance. Our method’s effectiveness is highlighted on the challenging MMLU-pro benchmark, where DFPE achieves a striking 17.1 percentage point gain over the best single model, reaching 71.4% accuracy. This strong performance is consistent across other standard benchmarks, with significant accuracy improvements of 4.4 points on AGIEval and 2.7 points on MMLU. Our results underscore that a systematic approach to ensemble construction - one that balances diversity, subject-specific competence, and adaptive weighting, can substantially enhance the generalization and robustness of LLMs on multifaceted language understanding tasks.
%U https://aclanthology.org/2026.findings-eacl.282/
%P 5326-5336
Markdown (Informal)
[DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance](https://aclanthology.org/2026.findings-eacl.282/) (Cohen et al., Findings 2026)
ACL