<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lehmann-etal-2024-beyond">
    <titleInfo>
        <title>Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jens</namePart>
        <namePart type="family">Lehmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dhananjay</namePart>
        <namePart type="family">Bhandiwad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Preetam</namePart>
        <namePart type="family">Gattogi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sahar</namePart>
        <namePart type="family">Vahdati</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Answering factual questions from heterogenous sources, such as graphs and text, is a key capacity of intelligent systems. Current approaches either (i) perform question answering over text and structured sources as separate pipelines followed by a merge step or (ii) provide an early integration, giving up the strengths of particular information sources. To solve this problem, we present “HumanIQ”, a method that teaches language models to dynamically combine retrieved information by imitating how humans use retrieval tools. Our approach couples a generic method for gathering human demonstrations of tool use with adaptive few-shot learning for tool augmented models. We show that HumanIQ confers significant benefits, including i) reducing the error rate of our strongest baseline (GPT-4) by over 50% across 3 benchmarks, (ii) improving human preference over responses from vanilla GPT-4 (45.3% wins, 46.7% ties, 8.0% loss), and (iii) outperforming numerous task-specific baselines.</abstract>
    <identifier type="citekey">lehmann-etal-2024-beyond</identifier>
    <identifier type="doi">10.1162/tacl_a_00671</identifier>
    <location>
        <url>https://aclanthology.org/2024.tacl-1.44</url>
    </location>
    <part>
        <date>2024</date>
        <detail type="volume"><number>12</number></detail>
        <extent unit="page">
            <start>786</start>
            <end>802</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources
%A Lehmann, Jens
%A Bhandiwad, Dhananjay
%A Gattogi, Preetam
%A Vahdati, Sahar
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F lehmann-etal-2024-beyond
%X Answering factual questions from heterogenous sources, such as graphs and text, is a key capacity of intelligent systems. Current approaches either (i) perform question answering over text and structured sources as separate pipelines followed by a merge step or (ii) provide an early integration, giving up the strengths of particular information sources. To solve this problem, we present “HumanIQ”, a method that teaches language models to dynamically combine retrieved information by imitating how humans use retrieval tools. Our approach couples a generic method for gathering human demonstrations of tool use with adaptive few-shot learning for tool augmented models. We show that HumanIQ confers significant benefits, including i) reducing the error rate of our strongest baseline (GPT-4) by over 50% across 3 benchmarks, (ii) improving human preference over responses from vanilla GPT-4 (45.3% wins, 46.7% ties, 8.0% loss), and (iii) outperforming numerous task-specific baselines.
%R 10.1162/tacl_a_00671
%U https://aclanthology.org/2024.tacl-1.44
%U https://doi.org/10.1162/tacl_a_00671
%P 786-802

Markdown (Informal)

[Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources](https://aclanthology.org/2024.tacl-1.44) (Lehmann et al., TACL 2024)

• Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources (Lehmann et al., TACL 2024)

ACL

• Jens Lehmann, Dhananjay Bhandiwad, Preetam Gattogi, and Sahar Vahdati. 2024. Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources. Transactions of the Association for Computational Linguistics, 12:786–802.