@inproceedings{chu-etal-2026-etracer,
title = "e{T}racer: Polarity-Aware Evidence Grounding",
author = "Chu, Bohao and
Wang, Qianli and
Damm, Hendrik and
Zhang, Shuning and
Wang, Hui and
Papenmeier, Andrea and
Lodde, Georg and
Livingstone, Elisabeth and
Friedrich, Christoph M. and
Fuhr, Norbert",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.314/",
pages = "7224--7253",
ISBN = "979-8-89176-459-0",
abstract = "Evidence grounding makes generated content verifiable by linking statements to their sources. However, effective verifiability requires two properties that existing methods fail to jointly provide: *verification granularity*, the ability to localize fine-grained evidence for each statement, and *verification completeness*, the ability to capture both support and contradiction. Existing methods either operate at granularities too coarse for rapid inspection or are support-only. We formalize *polarity-aware evidence grounding*: linking each response sentence to its contextual evidence with a supporting, contradicting, or irrelevant label. We construct **eTracer-Bench**, a human-annotated benchmark with 7,905 supporting and contradicting sentence pairs across seven domains, covering both explicit and implicit contradictions. We further propose **eTracer**, a post-hoc framework whose context-aware signed scorer recovers the full evidence map in a single forward pass per response, with localization and polarity emerging jointly from one mechanism. **eTracer** achieves the best overall Citation F1 of **82.39**, driven by a Contradict F1 of **89.20**. A pre-registered within-subjects user study ($n = 30$) shows that polarity-aware grounding nearly doubles contradiction detection over the document-level baseline (**27.9{\%} {\textrightarrow} 51.9{\%}**, Cohen{'}s $d = 0.82$, $p = 0.0003$), and suggests a false-completeness bias under which support-only grounding fails to improve over this baseline (**23.4{\%} vs. 27.9{\%}**). Dataset and code: https://github.com/chubohao/eTracer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2026-etracer">
<titleInfo>
<title>eTracer: Polarity-Aware Evidence Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bohao</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianli</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Damm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuning</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Papenmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Lodde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabeth</namePart>
<namePart type="family">Livingstone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norbert</namePart>
<namePart type="family">Fuhr</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Evidence grounding makes generated content verifiable by linking statements to their sources. However, effective verifiability requires two properties that existing methods fail to jointly provide: *verification granularity*, the ability to localize fine-grained evidence for each statement, and *verification completeness*, the ability to capture both support and contradiction. Existing methods either operate at granularities too coarse for rapid inspection or are support-only. We formalize *polarity-aware evidence grounding*: linking each response sentence to its contextual evidence with a supporting, contradicting, or irrelevant label. We construct **eTracer-Bench**, a human-annotated benchmark with 7,905 supporting and contradicting sentence pairs across seven domains, covering both explicit and implicit contradictions. We further propose **eTracer**, a post-hoc framework whose context-aware signed scorer recovers the full evidence map in a single forward pass per response, with localization and polarity emerging jointly from one mechanism. **eTracer** achieves the best overall Citation F1 of **82.39**, driven by a Contradict F1 of **89.20**. A pre-registered within-subjects user study (n = 30) shows that polarity-aware grounding nearly doubles contradiction detection over the document-level baseline (**27.9% → 51.9%**, Cohen’s d = 0.82, p = 0.0003), and suggests a false-completeness bias under which support-only grounding fails to improve over this baseline (**23.4% vs. 27.9%**). Dataset and code: https://github.com/chubohao/eTracer.</abstract>
<identifier type="citekey">chu-etal-2026-etracer</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.314/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>7224</start>
<end>7253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T eTracer: Polarity-Aware Evidence Grounding
%A Chu, Bohao
%A Wang, Qianli
%A Damm, Hendrik
%A Zhang, Shuning
%A Wang, Hui
%A Papenmeier, Andrea
%A Lodde, Georg
%A Livingstone, Elisabeth
%A Friedrich, Christoph M.
%A Fuhr, Norbert
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F chu-etal-2026-etracer
%X Evidence grounding makes generated content verifiable by linking statements to their sources. However, effective verifiability requires two properties that existing methods fail to jointly provide: *verification granularity*, the ability to localize fine-grained evidence for each statement, and *verification completeness*, the ability to capture both support and contradiction. Existing methods either operate at granularities too coarse for rapid inspection or are support-only. We formalize *polarity-aware evidence grounding*: linking each response sentence to its contextual evidence with a supporting, contradicting, or irrelevant label. We construct **eTracer-Bench**, a human-annotated benchmark with 7,905 supporting and contradicting sentence pairs across seven domains, covering both explicit and implicit contradictions. We further propose **eTracer**, a post-hoc framework whose context-aware signed scorer recovers the full evidence map in a single forward pass per response, with localization and polarity emerging jointly from one mechanism. **eTracer** achieves the best overall Citation F1 of **82.39**, driven by a Contradict F1 of **89.20**. A pre-registered within-subjects user study (n = 30) shows that polarity-aware grounding nearly doubles contradiction detection over the document-level baseline (**27.9% → 51.9%**, Cohen’s d = 0.82, p = 0.0003), and suggests a false-completeness bias under which support-only grounding fails to improve over this baseline (**23.4% vs. 27.9%**). Dataset and code: https://github.com/chubohao/eTracer.
%U https://aclanthology.org/2026.emnlp-main.314/
%P 7224-7253
Markdown (Informal)
[eTracer: Polarity-Aware Evidence Grounding](https://aclanthology.org/2026.emnlp-main.314/) (Chu et al., EMNLP 2026)
ACL
- Bohao Chu, Qianli Wang, Hendrik Damm, Shuning Zhang, Hui Wang, Andrea Papenmeier, Georg Lodde, Elisabeth Livingstone, Christoph M. Friedrich, and Norbert Fuhr. 2026. eTracer: Polarity-Aware Evidence Grounding. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 7224–7253, Budapest, Hungary. Association for Computational Linguistics.