@inproceedings{liu-etal-2026-littraceqa,
title = "{L}it{T}race{QA}: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering",
author = "Liu, Xuye and
Wang, Yimu and
Shi, Peng and
Xue, Bo and
Ke, Xiangrui and
Cai, Songcheng and
Choi, Kath and
Wu, Di and
Shi, Freda and
Czarnecki, Krzysztof",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.81/",
pages = "1146--1153",
ISBN = "979-8-89176-478-1",
abstract = "Scientific question answering is useful only when readers can recover the papers and evidence behind an answer. Yet many benchmarks either provide the source document or score only the final response, obscuring failures in literature retrieval and evidence localization. We present LitTraceQA, a literature-grounded question answering benchmark in which a system must return a connected trace: canonical paper identifiers, typed evidence locations, and a checkable answer. The collection contains 4,978 unique questions grounded in 4,859 papers and covers tables, figures, text spans, equations or algorithms, and citation contexts. Of these questions, 64.85{\%} require multiple papers; answers use multiple-choice or structured-table formats; and 61.9{\%} are missed by every memory-only challenger used during construction. We describe a generate-and-ground-challenge pipeline and an evaluation protocol that reports paper retrieval, evidence grounding, answer correctness, and strict joint success separately. LitTraceQA therefore tests whether scientific QA systems can produce answers whose provenance is inspectable, rather than merely plausible."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-littraceqa">
<titleInfo>
<title>LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuye</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangrui</namePart>
<namePart type="family">Ke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songcheng</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kath</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freda</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Czarnecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>Scientific question answering is useful only when readers can recover the papers and evidence behind an answer. Yet many benchmarks either provide the source document or score only the final response, obscuring failures in literature retrieval and evidence localization. We present LitTraceQA, a literature-grounded question answering benchmark in which a system must return a connected trace: canonical paper identifiers, typed evidence locations, and a checkable answer. The collection contains 4,978 unique questions grounded in 4,859 papers and covers tables, figures, text spans, equations or algorithms, and citation contexts. Of these questions, 64.85% require multiple papers; answers use multiple-choice or structured-table formats; and 61.9% are missed by every memory-only challenger used during construction. We describe a generate-and-ground-challenge pipeline and an evaluation protocol that reports paper retrieval, evidence grounding, answer correctness, and strict joint success separately. LitTraceQA therefore tests whether scientific QA systems can produce answers whose provenance is inspectable, rather than merely plausible.</abstract>
<identifier type="citekey">liu-etal-2026-littraceqa</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.81/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1146</start>
<end>1153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering
%A Liu, Xuye
%A Wang, Yimu
%A Shi, Peng
%A Xue, Bo
%A Ke, Xiangrui
%A Cai, Songcheng
%A Choi, Kath
%A Wu, Di
%A Shi, Freda
%A Czarnecki, Krzysztof
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F liu-etal-2026-littraceqa
%X Scientific question answering is useful only when readers can recover the papers and evidence behind an answer. Yet many benchmarks either provide the source document or score only the final response, obscuring failures in literature retrieval and evidence localization. We present LitTraceQA, a literature-grounded question answering benchmark in which a system must return a connected trace: canonical paper identifiers, typed evidence locations, and a checkable answer. The collection contains 4,978 unique questions grounded in 4,859 papers and covers tables, figures, text spans, equations or algorithms, and citation contexts. Of these questions, 64.85% require multiple papers; answers use multiple-choice or structured-table formats; and 61.9% are missed by every memory-only challenger used during construction. We describe a generate-and-ground-challenge pipeline and an evaluation protocol that reports paper retrieval, evidence grounding, answer correctness, and strict joint success separately. LitTraceQA therefore tests whether scientific QA systems can produce answers whose provenance is inspectable, rather than merely plausible.
%U https://aclanthology.org/2026.groundlm-1.81/
%P 1146-1153
Markdown (Informal)
[LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering](https://aclanthology.org/2026.groundlm-1.81/) (Liu et al., GroundLM 2026)
ACL
- Xuye Liu, Yimu Wang, Peng Shi, Bo Xue, Xiangrui Ke, Songcheng Cai, Kath Choi, Di Wu, Freda Shi, and Krzysztof Czarnecki. 2026. LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering. In Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026), pages 1146–1153, Budapest, Hungary. Association for Computational Linguistics.