@inproceedings{guo-etal-2024-sample,
title = "Sample Design Engineering: An Empirical Study on Designing Better Fine-Tuning Samples for Information Extraction with {LLM}s",
author = "Guo, Biyang and
Wang, He and
Xiao, Wenyilin and
Chen, Hong and
Lee, ZhuXin and
Han, Songqiao and
Huang, Hailiang",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.43",
doi = "10.18653/v1/2024.emnlp-industry.43",
pages = "573--594",
abstract = "Large language models (LLMs) have achieved significant leadership in many NLP tasks, but aligning structured output with generative models in information extraction (IE) tasks remains a challenge. Prompt Engineering (PE) is renowned for improving IE performance through prompt modifications. However, the realm of the sample design for downstream fine-tuning, crucial for task-specific LLM adaptation, is largely unexplored. This paper introduces **Sample Design Engineering** (SDE), a methodical approach to enhancing LLMs{'} post-tuning performance on IE tasks by refining input, output, and reasoning designs. Through extensive ID and OOD experiments across six LLMs, we first assess the impact of various design options on IE performance, revealing several intriguing patterns. Based on these insights, we then propose an integrated SDE strategy and validate its consistent superiority over heuristic sample designs on three complex IE tasks with four additional LLMs, demonstrating the generality of our method. Additionally, analyses of LLMs{'} inherent prompt/output perplexity, zero-shot, and ICL abilities illustrate that good PE strategies may not always translate to good SDE strategies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-sample">
<titleInfo>
<title>Sample Design Engineering: An Empirical Study on Designing Better Fine-Tuning Samples for Information Extraction with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Biyang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyilin</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ZhuXin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songqiao</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailiang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoţiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have achieved significant leadership in many NLP tasks, but aligning structured output with generative models in information extraction (IE) tasks remains a challenge. Prompt Engineering (PE) is renowned for improving IE performance through prompt modifications. However, the realm of the sample design for downstream fine-tuning, crucial for task-specific LLM adaptation, is largely unexplored. This paper introduces **Sample Design Engineering** (SDE), a methodical approach to enhancing LLMs’ post-tuning performance on IE tasks by refining input, output, and reasoning designs. Through extensive ID and OOD experiments across six LLMs, we first assess the impact of various design options on IE performance, revealing several intriguing patterns. Based on these insights, we then propose an integrated SDE strategy and validate its consistent superiority over heuristic sample designs on three complex IE tasks with four additional LLMs, demonstrating the generality of our method. Additionally, analyses of LLMs’ inherent prompt/output perplexity, zero-shot, and ICL abilities illustrate that good PE strategies may not always translate to good SDE strategies.</abstract>
<identifier type="citekey">guo-etal-2024-sample</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-industry.43</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-industry.43</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>573</start>
<end>594</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sample Design Engineering: An Empirical Study on Designing Better Fine-Tuning Samples for Information Extraction with LLMs
%A Guo, Biyang
%A Wang, He
%A Xiao, Wenyilin
%A Chen, Hong
%A Lee, ZhuXin
%A Han, Songqiao
%A Huang, Hailiang
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F guo-etal-2024-sample
%X Large language models (LLMs) have achieved significant leadership in many NLP tasks, but aligning structured output with generative models in information extraction (IE) tasks remains a challenge. Prompt Engineering (PE) is renowned for improving IE performance through prompt modifications. However, the realm of the sample design for downstream fine-tuning, crucial for task-specific LLM adaptation, is largely unexplored. This paper introduces **Sample Design Engineering** (SDE), a methodical approach to enhancing LLMs’ post-tuning performance on IE tasks by refining input, output, and reasoning designs. Through extensive ID and OOD experiments across six LLMs, we first assess the impact of various design options on IE performance, revealing several intriguing patterns. Based on these insights, we then propose an integrated SDE strategy and validate its consistent superiority over heuristic sample designs on three complex IE tasks with four additional LLMs, demonstrating the generality of our method. Additionally, analyses of LLMs’ inherent prompt/output perplexity, zero-shot, and ICL abilities illustrate that good PE strategies may not always translate to good SDE strategies.
%R 10.18653/v1/2024.emnlp-industry.43
%U https://aclanthology.org/2024.emnlp-industry.43
%U https://doi.org/10.18653/v1/2024.emnlp-industry.43
%P 573-594
Markdown (Informal)
[Sample Design Engineering: An Empirical Study on Designing Better Fine-Tuning Samples for Information Extraction with LLMs](https://aclanthology.org/2024.emnlp-industry.43) (Guo et al., EMNLP 2024)
ACL
- Biyang Guo, He Wang, Wenyilin Xiao, Hong Chen, ZhuXin Lee, Songqiao Han, and Hailiang Huang. 2024. Sample Design Engineering: An Empirical Study on Designing Better Fine-Tuning Samples for Information Extraction with LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 573–594, Miami, Florida, US. Association for Computational Linguistics.