@inproceedings{anikina-etal-2025-reverse,
title = "Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution",
author = {Anikina, Tatiana and
Binder, Arne and
Harbecke, David and
Varanasi, Stalin and
Hennig, Leonhard and
Ostermann, Simon and
M{\"o}ller, Sebastian and
Genabith, Josef Van},
editor = "Adlakha, Vaibhav and
Chronopoulou, Alexandra and
Li, Xiang Lorraine and
Majumder, Bodhisattwa Prasad and
Shi, Freda and
Vernikos, Giorgos",
booktitle = "Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)",
month = may,
year = "2025",
address = "Albuquerque, NM",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.repl4nlp-1.9/",
doi = "10.18653/v1/2025.repl4nlp-1.9",
pages = "108--119",
ISBN = "979-8-89176-245-9",
abstract = "In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as usually done in probing), we explore the effectiveness of embeddings from multiple simple source tasks on a single target task. We select coreference resolution, a linguistically complex problem requiring contextual understanding, as focus target task, and test the usefulness of embeddings from comparably simpler tasks tasks such as paraphrase detection, named entity recognition, and relation extraction. Through systematic experiments, we evaluate the impact of individual and combined task embeddings. Our findings reveal that task embeddings vary significantly in utility for coreference resolution, with semantic similarity tasks (e.g., paraphrase detection) proving most beneficial. Additionally, representations from intermediate layers of fine-tuned models often outperform those from final layers. Combining embeddings from multiple tasks consistently improves performance, with attention-based aggregation yielding substantial gains. These insights shed light on relationships between task-specific representations and their adaptability to complex downstream tasks, encouraging further exploration of embedding-level task transfer. Our source code is publicly available under https://github.com/Cora4NLP/multi-task-knowledge-transfer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anikina-etal-2025-reverse">
<titleInfo>
<title>Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Anikina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arne</namePart>
<namePart type="family">Binder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Harbecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stalin</namePart>
<namePart type="family">Varanasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonhard</namePart>
<namePart type="family">Hennig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Ostermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vaibhav</namePart>
<namePart type="family">Adlakha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Chronopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="given">Lorraine</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bodhisattwa</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freda</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giorgos</namePart>
<namePart type="family">Vernikos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, NM</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-245-9</identifier>
</relatedItem>
<abstract>In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as usually done in probing), we explore the effectiveness of embeddings from multiple simple source tasks on a single target task. We select coreference resolution, a linguistically complex problem requiring contextual understanding, as focus target task, and test the usefulness of embeddings from comparably simpler tasks tasks such as paraphrase detection, named entity recognition, and relation extraction. Through systematic experiments, we evaluate the impact of individual and combined task embeddings. Our findings reveal that task embeddings vary significantly in utility for coreference resolution, with semantic similarity tasks (e.g., paraphrase detection) proving most beneficial. Additionally, representations from intermediate layers of fine-tuned models often outperform those from final layers. Combining embeddings from multiple tasks consistently improves performance, with attention-based aggregation yielding substantial gains. These insights shed light on relationships between task-specific representations and their adaptability to complex downstream tasks, encouraging further exploration of embedding-level task transfer. Our source code is publicly available under https://github.com/Cora4NLP/multi-task-knowledge-transfer.</abstract>
<identifier type="citekey">anikina-etal-2025-reverse</identifier>
<identifier type="doi">10.18653/v1/2025.repl4nlp-1.9</identifier>
<location>
<url>https://aclanthology.org/2025.repl4nlp-1.9/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>108</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution
%A Anikina, Tatiana
%A Binder, Arne
%A Harbecke, David
%A Varanasi, Stalin
%A Hennig, Leonhard
%A Ostermann, Simon
%A Möller, Sebastian
%A Genabith, Josef Van
%Y Adlakha, Vaibhav
%Y Chronopoulou, Alexandra
%Y Li, Xiang Lorraine
%Y Majumder, Bodhisattwa Prasad
%Y Shi, Freda
%Y Vernikos, Giorgos
%S Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, NM
%@ 979-8-89176-245-9
%F anikina-etal-2025-reverse
%X In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as usually done in probing), we explore the effectiveness of embeddings from multiple simple source tasks on a single target task. We select coreference resolution, a linguistically complex problem requiring contextual understanding, as focus target task, and test the usefulness of embeddings from comparably simpler tasks tasks such as paraphrase detection, named entity recognition, and relation extraction. Through systematic experiments, we evaluate the impact of individual and combined task embeddings. Our findings reveal that task embeddings vary significantly in utility for coreference resolution, with semantic similarity tasks (e.g., paraphrase detection) proving most beneficial. Additionally, representations from intermediate layers of fine-tuned models often outperform those from final layers. Combining embeddings from multiple tasks consistently improves performance, with attention-based aggregation yielding substantial gains. These insights shed light on relationships between task-specific representations and their adaptability to complex downstream tasks, encouraging further exploration of embedding-level task transfer. Our source code is publicly available under https://github.com/Cora4NLP/multi-task-knowledge-transfer.
%R 10.18653/v1/2025.repl4nlp-1.9
%U https://aclanthology.org/2025.repl4nlp-1.9/
%U https://doi.org/10.18653/v1/2025.repl4nlp-1.9
%P 108-119
Markdown (Informal)
[Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution](https://aclanthology.org/2025.repl4nlp-1.9/) (Anikina et al., RepL4NLP 2025)
ACL
- Tatiana Anikina, Arne Binder, David Harbecke, Stalin Varanasi, Leonhard Hennig, Simon Ostermann, Sebastian Möller, and Josef Van Genabith. 2025. Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution. In Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025), pages 108–119, Albuquerque, NM. Association for Computational Linguistics.