@inproceedings{xu-etal-2026-sage-slot,
title = "{SAGE}: Slot-Aware Grounded Evidence Acquisition for {L}it{T}race{QA}",
author = "Xu, Gang and
Huang, Ce and
Pan, Yushan and
Wang, Wei",
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-1.87/",
pages = "1187--1195",
ISBN = "979-8-89176-478-1",
abstract = "Literature-grounded question answering requires a system to retrieve the right papers, locate answer-bearing content in heterogeneous PDFs, and return an answer whose evidence locators can be restored from the retrieved documents. We describe SAGE, an evidence-first system for LitTraceQA that separates these dependencies. A query-only evidence plan converts a question and its public answer contract into typed evidence obligations. The system retrieves candidate papers from official metadata, acquires and parses their PDFs into provenance-preserving text and object records, reranks record-aware text and image projections, and selects a bounded evidence package with explicit slots, modality, and cross-paper coverage priorities. A multimodal generator then answers with the fixed package, while deterministic normalization permits only candidate paper IDs and locators recoverable from selected parser records. Overall, SAGE adopts an evidence-first design that separates paper retrieval, fine-grained evidence acquisition, set-level selection, and grounded answer generation while preserving provenance throughout the pipeline. On the official evaluation, the system performs strongly in paper retrieval and multiple-choice answering, whereas fine-grained evidence grounding and structured table prediction remain more challenging."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-sage-slot">
<titleInfo>
<title>SAGE: Slot-Aware Grounded Evidence Acquisition for LitTraceQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ce</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yushan</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</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>Literature-grounded question answering requires a system to retrieve the right papers, locate answer-bearing content in heterogeneous PDFs, and return an answer whose evidence locators can be restored from the retrieved documents. We describe SAGE, an evidence-first system for LitTraceQA that separates these dependencies. A query-only evidence plan converts a question and its public answer contract into typed evidence obligations. The system retrieves candidate papers from official metadata, acquires and parses their PDFs into provenance-preserving text and object records, reranks record-aware text and image projections, and selects a bounded evidence package with explicit slots, modality, and cross-paper coverage priorities. A multimodal generator then answers with the fixed package, while deterministic normalization permits only candidate paper IDs and locators recoverable from selected parser records. Overall, SAGE adopts an evidence-first design that separates paper retrieval, fine-grained evidence acquisition, set-level selection, and grounded answer generation while preserving provenance throughout the pipeline. On the official evaluation, the system performs strongly in paper retrieval and multiple-choice answering, whereas fine-grained evidence grounding and structured table prediction remain more challenging.</abstract>
<identifier type="citekey">xu-etal-2026-sage-slot</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.87/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1187</start>
<end>1195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAGE: Slot-Aware Grounded Evidence Acquisition for LitTraceQA
%A Xu, Gang
%A Huang, Ce
%A Pan, Yushan
%A Wang, Wei
%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 xu-etal-2026-sage-slot
%X Literature-grounded question answering requires a system to retrieve the right papers, locate answer-bearing content in heterogeneous PDFs, and return an answer whose evidence locators can be restored from the retrieved documents. We describe SAGE, an evidence-first system for LitTraceQA that separates these dependencies. A query-only evidence plan converts a question and its public answer contract into typed evidence obligations. The system retrieves candidate papers from official metadata, acquires and parses their PDFs into provenance-preserving text and object records, reranks record-aware text and image projections, and selects a bounded evidence package with explicit slots, modality, and cross-paper coverage priorities. A multimodal generator then answers with the fixed package, while deterministic normalization permits only candidate paper IDs and locators recoverable from selected parser records. Overall, SAGE adopts an evidence-first design that separates paper retrieval, fine-grained evidence acquisition, set-level selection, and grounded answer generation while preserving provenance throughout the pipeline. On the official evaluation, the system performs strongly in paper retrieval and multiple-choice answering, whereas fine-grained evidence grounding and structured table prediction remain more challenging.
%U https://aclanthology.org/2026.groundlm-1.87/
%P 1187-1195
Markdown (Informal)
[SAGE: Slot-Aware Grounded Evidence Acquisition for LitTraceQA](https://aclanthology.org/2026.groundlm-1.87/) (Xu et al., GroundLM 2026)
ACL
- Gang Xu, Ce Huang, Yushan Pan, and Wei Wang. 2026. SAGE: Slot-Aware Grounded Evidence Acquisition for LitTraceQA. In Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026), pages 1187–1195, Budapest, Hungary. Association for Computational Linguistics.