@inproceedings{nathan-etal-2024-probing,
title = "Can probing classifiers reveal the learning by contact center large language models?: No, it doesn{'}t!",
author = "Nathan, Varun and
Kumar, Ayush and
Ingle, Digvijay",
editor = "Tafreshi, Shabnam and
Akula, Arjun and
Sedoc, Jo{\~a}o and
Drozd, Aleksandr and
Rogers, Anna and
Rumshisky, Anna",
booktitle = "Proceedings of the Fifth Workshop on Insights from Negative Results in NLP",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.insights-1.12",
doi = "10.18653/v1/2024.insights-1.12",
pages = "92--100",
abstract = "Fine-tuning large language models (LLMs) with domain-specific instruction dataset has emerged as an effective method to enhance their domain-specific understanding. Yet, there is limited work that examines the core characteristics acquired during this process. In this study, we benchmark the fundamental characteristics learned by contact-center (CC) domain specific instruction fine-tuned LLMs with out-of-the-box (OOB) LLMs via probing tasks encompassing conversational, channel, and automatic speech recognition (ASR) properties. We explore different LLM architectures (Flan-T5 and Llama) and sizes (3B, 7B, 11B, 13B). Our findings reveal remarkable effectiveness of CC-LLMs on the in-domain downstream tasks, with improvement in response acceptability by over 48{\%} compared to OOB-LLMs. However, we observe that the performance of probing classifiers are relatively similar and does not reflect the performance of in-domain downstream tasks. A similar observation is also noted on SentEval dataset that assess capabilities of models in terms of surface, syntactic, and semantic information through probing tasks. Our study challenges the premise that probing classifiers can reveal the fundamental characteristics learned by large language models and is reflective of the downstream task performance, via a case-study of LLMs tuned for contact center domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nathan-etal-2024-probing">
<titleInfo>
<title>Can probing classifiers reveal the learning by contact center large language models?: No, it doesn’t!</title>
</titleInfo>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Nathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Digvijay</namePart>
<namePart type="family">Ingle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fine-tuning large language models (LLMs) with domain-specific instruction dataset has emerged as an effective method to enhance their domain-specific understanding. Yet, there is limited work that examines the core characteristics acquired during this process. In this study, we benchmark the fundamental characteristics learned by contact-center (CC) domain specific instruction fine-tuned LLMs with out-of-the-box (OOB) LLMs via probing tasks encompassing conversational, channel, and automatic speech recognition (ASR) properties. We explore different LLM architectures (Flan-T5 and Llama) and sizes (3B, 7B, 11B, 13B). Our findings reveal remarkable effectiveness of CC-LLMs on the in-domain downstream tasks, with improvement in response acceptability by over 48% compared to OOB-LLMs. However, we observe that the performance of probing classifiers are relatively similar and does not reflect the performance of in-domain downstream tasks. A similar observation is also noted on SentEval dataset that assess capabilities of models in terms of surface, syntactic, and semantic information through probing tasks. Our study challenges the premise that probing classifiers can reveal the fundamental characteristics learned by large language models and is reflective of the downstream task performance, via a case-study of LLMs tuned for contact center domain.</abstract>
<identifier type="citekey">nathan-etal-2024-probing</identifier>
<identifier type="doi">10.18653/v1/2024.insights-1.12</identifier>
<location>
<url>https://aclanthology.org/2024.insights-1.12</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>92</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can probing classifiers reveal the learning by contact center large language models?: No, it doesn’t!
%A Nathan, Varun
%A Kumar, Ayush
%A Ingle, Digvijay
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Sedoc, João
%Y Drozd, Aleksandr
%Y Rogers, Anna
%Y Rumshisky, Anna
%S Proceedings of the Fifth Workshop on Insights from Negative Results in NLP
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F nathan-etal-2024-probing
%X Fine-tuning large language models (LLMs) with domain-specific instruction dataset has emerged as an effective method to enhance their domain-specific understanding. Yet, there is limited work that examines the core characteristics acquired during this process. In this study, we benchmark the fundamental characteristics learned by contact-center (CC) domain specific instruction fine-tuned LLMs with out-of-the-box (OOB) LLMs via probing tasks encompassing conversational, channel, and automatic speech recognition (ASR) properties. We explore different LLM architectures (Flan-T5 and Llama) and sizes (3B, 7B, 11B, 13B). Our findings reveal remarkable effectiveness of CC-LLMs on the in-domain downstream tasks, with improvement in response acceptability by over 48% compared to OOB-LLMs. However, we observe that the performance of probing classifiers are relatively similar and does not reflect the performance of in-domain downstream tasks. A similar observation is also noted on SentEval dataset that assess capabilities of models in terms of surface, syntactic, and semantic information through probing tasks. Our study challenges the premise that probing classifiers can reveal the fundamental characteristics learned by large language models and is reflective of the downstream task performance, via a case-study of LLMs tuned for contact center domain.
%R 10.18653/v1/2024.insights-1.12
%U https://aclanthology.org/2024.insights-1.12
%U https://doi.org/10.18653/v1/2024.insights-1.12
%P 92-100
Markdown (Informal)
[Can probing classifiers reveal the learning by contact center large language models?: No, it doesn’t!](https://aclanthology.org/2024.insights-1.12) (Nathan et al., insights-WS 2024)
ACL