@inproceedings{ye-etal-2023-complementary,
title = "Complementary Explanations for Effective In-Context Learning",
author = "Ye, Xi and
Iyer, Srinivasan and
Celikyilmaz, Asli and
Stoyanov, Veselin and
Durrett, Greg and
Pasunuru, Ramakanth",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.273",
doi = "10.18653/v1/2023.findings-acl.273",
pages = "4469--4484",
abstract = "Large language models (LLMs) have exhibited remarkable capabilities in learning from expla- nations in prompts, but there has been limited understanding of exactly how these explana- tions function or why they are effective. This work aims to better understand the mechanisms by which explanations are used for in-context learning. We first study the impact of two dif- ferent factors on the performance of prompts with explanations: the computation trace (the way the solution is decomposed) and the natural language used to express the prompt. By per- turbing explanations on three controlled tasks, we show that both factors contribute to the ef- fectiveness of explanations. We further study how to form maximally effective sets of expla- nations for solving a given test query. We find that LLMs can benefit from the complemen- tarity of the explanation set: diverse reasoning skills shown by different exemplars can lead to better performance. Therefore, we propose a maximal marginal relevance-based exemplar selection approach for constructing exemplar sets that are both relevant as well as comple- mentary, which successfully improves the in- context learning performance across three real- world tasks on multiple LLMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-etal-2023-complementary">
<titleInfo>
<title>Complementary Explanations for Effective In-Context Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinivasan</namePart>
<namePart type="family">Iyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veselin</namePart>
<namePart type="family">Stoyanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramakanth</namePart>
<namePart type="family">Pasunuru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<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">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have exhibited remarkable capabilities in learning from expla- nations in prompts, but there has been limited understanding of exactly how these explana- tions function or why they are effective. This work aims to better understand the mechanisms by which explanations are used for in-context learning. We first study the impact of two dif- ferent factors on the performance of prompts with explanations: the computation trace (the way the solution is decomposed) and the natural language used to express the prompt. By per- turbing explanations on three controlled tasks, we show that both factors contribute to the ef- fectiveness of explanations. We further study how to form maximally effective sets of expla- nations for solving a given test query. We find that LLMs can benefit from the complemen- tarity of the explanation set: diverse reasoning skills shown by different exemplars can lead to better performance. Therefore, we propose a maximal marginal relevance-based exemplar selection approach for constructing exemplar sets that are both relevant as well as comple- mentary, which successfully improves the in- context learning performance across three real- world tasks on multiple LLMs.</abstract>
<identifier type="citekey">ye-etal-2023-complementary</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.273</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.273</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4469</start>
<end>4484</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Complementary Explanations for Effective In-Context Learning
%A Ye, Xi
%A Iyer, Srinivasan
%A Celikyilmaz, Asli
%A Stoyanov, Veselin
%A Durrett, Greg
%A Pasunuru, Ramakanth
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ye-etal-2023-complementary
%X Large language models (LLMs) have exhibited remarkable capabilities in learning from expla- nations in prompts, but there has been limited understanding of exactly how these explana- tions function or why they are effective. This work aims to better understand the mechanisms by which explanations are used for in-context learning. We first study the impact of two dif- ferent factors on the performance of prompts with explanations: the computation trace (the way the solution is decomposed) and the natural language used to express the prompt. By per- turbing explanations on three controlled tasks, we show that both factors contribute to the ef- fectiveness of explanations. We further study how to form maximally effective sets of expla- nations for solving a given test query. We find that LLMs can benefit from the complemen- tarity of the explanation set: diverse reasoning skills shown by different exemplars can lead to better performance. Therefore, we propose a maximal marginal relevance-based exemplar selection approach for constructing exemplar sets that are both relevant as well as comple- mentary, which successfully improves the in- context learning performance across three real- world tasks on multiple LLMs.
%R 10.18653/v1/2023.findings-acl.273
%U https://aclanthology.org/2023.findings-acl.273
%U https://doi.org/10.18653/v1/2023.findings-acl.273
%P 4469-4484
Markdown (Informal)
[Complementary Explanations for Effective In-Context Learning](https://aclanthology.org/2023.findings-acl.273) (Ye et al., Findings 2023)
ACL
- Xi Ye, Srinivasan Iyer, Asli Celikyilmaz, Veselin Stoyanov, Greg Durrett, and Ramakanth Pasunuru. 2023. Complementary Explanations for Effective In-Context Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4469–4484, Toronto, Canada. Association for Computational Linguistics.