<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sundar-heck-2023-ctbls">
    <titleInfo>
        <title>cTBLS: Augmenting Large Language Models with Conversational Tables</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anirudh</namePart>
        <namePart type="given">S</namePart>
        <namePart type="family">Sundar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Larry</namePart>
        <namePart type="family">Heck</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>Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abhinav</namePart>
            <namePart type="family">Rastogi</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>Optimizing accuracy and performance while eliminating hallucinations of open-domain conversational large language models (LLMs) is an open research challenge. A particularly promising direction is to augment and ground LLMs with information from structured sources. This paper introduces Conversational Tables cTBLS, a three-step architecture to retrieve and generate dialogue responses grounded on retrieved tabular information. cTBLS uses Transformer encoder embeddings for Dense Table Retrieval and obtains up to 125% relative improvement over the retriever in the previous state-of-the-art system on the HyrbiDialogue dataset. cTBLS then uses a shared process between encoder and decoder models to perform a coarse+fine tabular knowledge (e.g., cell) ranking combined with a GPT-3.5 LLM response generator to yield a 2x relative improvement in ROUGE scores. Finally, human evaluators prefer cTBLs +80% of the time (coherency, fluency) and judge informativeness to be 4x better than the previous state-of-the-art.</abstract>
    <identifier type="citekey">sundar-heck-2023-ctbls</identifier>
    <identifier type="doi">10.18653/v1/2023.nlp4convai-1.6</identifier>
    <location>
        <url>https://aclanthology.org/2023.nlp4convai-1.6</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>59</start>
            <end>70</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T cTBLS: Augmenting Large Language Models with Conversational Tables
%A Sundar, Anirudh S.
%A Heck, Larry
%Y Chen, Yun-Nung
%Y Rastogi, Abhinav
%S Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F sundar-heck-2023-ctbls
%X Optimizing accuracy and performance while eliminating hallucinations of open-domain conversational large language models (LLMs) is an open research challenge. A particularly promising direction is to augment and ground LLMs with information from structured sources. This paper introduces Conversational Tables cTBLS, a three-step architecture to retrieve and generate dialogue responses grounded on retrieved tabular information. cTBLS uses Transformer encoder embeddings for Dense Table Retrieval and obtains up to 125% relative improvement over the retriever in the previous state-of-the-art system on the HyrbiDialogue dataset. cTBLS then uses a shared process between encoder and decoder models to perform a coarse+fine tabular knowledge (e.g., cell) ranking combined with a GPT-3.5 LLM response generator to yield a 2x relative improvement in ROUGE scores. Finally, human evaluators prefer cTBLs +80% of the time (coherency, fluency) and judge informativeness to be 4x better than the previous state-of-the-art.
%R 10.18653/v1/2023.nlp4convai-1.6
%U https://aclanthology.org/2023.nlp4convai-1.6
%U https://doi.org/10.18653/v1/2023.nlp4convai-1.6
%P 59-70

Markdown (Informal)

[cTBLS: Augmenting Large Language Models with Conversational Tables](https://aclanthology.org/2023.nlp4convai-1.6) (Sundar & Heck, NLP4ConvAI 2023)

• cTBLS: Augmenting Large Language Models with Conversational Tables (Sundar & Heck, NLP4ConvAI 2023)

ACL

• Anirudh S. Sundar and Larry Heck. 2023. cTBLS: Augmenting Large Language Models with Conversational Tables. In Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023), pages 59–70, Toronto, Canada. Association for Computational Linguistics.