<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="merrill-etal-2024-evaluating">
    <titleInfo>
        <title>Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">William</namePart>
        <namePart type="family">Merrill</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noah</namePart>
        <namePart type="family">Smith</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanai</namePart>
        <namePart type="family">Elazar</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</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>How novel are texts generated by language models (LMs) relative to their training corpora? In this work, we investigate the extent to which modern LMs generate n-grams from their training data, evaluating both (i) the probability LMs assign to complete training n-grams and (ii) n-novelty, the proportion of n-grams generated by an LM that did not appear in the training data (for arbitrarily large n). To enable arbitrary-length n-gram search over a corpus in constant time w.r.t. corpus size, we develop Rusty-DAWG, a novel search tool inspired by indexing of genomic data. We compare the novelty of LM-generated text to human-written text and explore factors that affect generation novelty, focusing on the Pythia models. We find that, for n &gt; 4, LM-generated text is less novel than human-written text, though it is more novel for smaller n. Larger LMs and more constrained decoding strategies both decrease novelty. Finally, we show that LMs complete n-grams with lower loss if they are more frequent in the training data. Overall, our results reveal factors influencing the novelty of LM-generated text, and we release Rusty-DAWG to facilitate further pretraining data research.</abstract>
    <identifier type="citekey">merrill-etal-2024-evaluating</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.800</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>14459</start>
            <end>14473</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG
%A Merrill, William
%A Smith, Noah
%A Elazar, Yanai
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F merrill-etal-2024-evaluating
%X How novel are texts generated by language models (LMs) relative to their training corpora? In this work, we investigate the extent to which modern LMs generate n-grams from their training data, evaluating both (i) the probability LMs assign to complete training n-grams and (ii) n-novelty, the proportion of n-grams generated by an LM that did not appear in the training data (for arbitrarily large n). To enable arbitrary-length n-gram search over a corpus in constant time w.r.t. corpus size, we develop Rusty-DAWG, a novel search tool inspired by indexing of genomic data. We compare the novelty of LM-generated text to human-written text and explore factors that affect generation novelty, focusing on the Pythia models. We find that, for n > 4, LM-generated text is less novel than human-written text, though it is more novel for smaller n. Larger LMs and more constrained decoding strategies both decrease novelty. Finally, we show that LMs complete n-grams with lower loss if they are more frequent in the training data. Overall, our results reveal factors influencing the novelty of LM-generated text, and we release Rusty-DAWG to facilitate further pretraining data research.
%U https://aclanthology.org/2024.emnlp-main.800
%P 14459-14473

Markdown (Informal)

[Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG](https://aclanthology.org/2024.emnlp-main.800) (Merrill et al., EMNLP 2024)

• Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG (Merrill et al., EMNLP 2024)

ACL

• William Merrill, Noah Smith, and Yanai Elazar. 2024. Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14459–14473, Miami, Florida, USA. Association for Computational Linguistics.