@inproceedings{liu-etal-2026-trace-fine,
title = "{TRACE}: A Fine-Grained Benchmark for Temporal Reasoning and Chronological Knowledge Editing over Large Language Models",
author = "Liu, Xiliang and
Xie, Zhiwen and
Wong, Derek F.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1045/",
pages = "22130--22143",
ISBN = "979-8-89176-462-0",
abstract = "Knowledge editing algorithms have emerged as an efficient paradigm for updating parametric facts in Large Language Models (LLMs) without full retraining. However, existing benchmarks primarily focus on isolated, static facts. While a few temporal datasets exist, they are frequently bottlenecked by coarse temporal granularity, severe relation imbalance, and a critical lack of a priori knowledge validation, which can conflate inherent model deficits with editing failures. To address these structural limitations, we introduce TRACE, a fine-grained Temporal Reasoning And Chronological Editing benchmark. Using exact-match a priori probing, TRACE dynamically constructs model-specific, non-mutually exclusive chronological event chains. Featuring over 16,000 customized test cases across two distinct operational setups (Modify and Insert), TRACE provides a comprehensive 7-dimensional metric matrix. It extends simple fact recall with relation-constrained counterfactual injection and sequential temporal logic probes that test timeline integrity. Our evaluation of 6 representative baselines (FT, IKE, ROME, GRACE, LoRA, WISE) on Llama-3.2-3B and GPT-J-6B identifies widespread temporal interference in the studied settings: editing a single timestamp often sharply degrades recall of adjacent historical and future facts. The consistently weak bidirectional inference after editing further suggests that the evaluated methods tend to introduce shallow, syntax-sensitive patches rather than integrate the edit into a chronological network. Our code, the EasyEdit snapshot used for the experiments, and the benchmark are publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-trace-fine">
<titleInfo>
<title>TRACE: A Fine-Grained Benchmark for Temporal Reasoning and Chronological Knowledge Editing over Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiliang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwen</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Knowledge editing algorithms have emerged as an efficient paradigm for updating parametric facts in Large Language Models (LLMs) without full retraining. However, existing benchmarks primarily focus on isolated, static facts. While a few temporal datasets exist, they are frequently bottlenecked by coarse temporal granularity, severe relation imbalance, and a critical lack of a priori knowledge validation, which can conflate inherent model deficits with editing failures. To address these structural limitations, we introduce TRACE, a fine-grained Temporal Reasoning And Chronological Editing benchmark. Using exact-match a priori probing, TRACE dynamically constructs model-specific, non-mutually exclusive chronological event chains. Featuring over 16,000 customized test cases across two distinct operational setups (Modify and Insert), TRACE provides a comprehensive 7-dimensional metric matrix. It extends simple fact recall with relation-constrained counterfactual injection and sequential temporal logic probes that test timeline integrity. Our evaluation of 6 representative baselines (FT, IKE, ROME, GRACE, LoRA, WISE) on Llama-3.2-3B and GPT-J-6B identifies widespread temporal interference in the studied settings: editing a single timestamp often sharply degrades recall of adjacent historical and future facts. The consistently weak bidirectional inference after editing further suggests that the evaluated methods tend to introduce shallow, syntax-sensitive patches rather than integrate the edit into a chronological network. Our code, the EasyEdit snapshot used for the experiments, and the benchmark are publicly available.</abstract>
<identifier type="citekey">liu-etal-2026-trace-fine</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1045/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>22130</start>
<end>22143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRACE: A Fine-Grained Benchmark for Temporal Reasoning and Chronological Knowledge Editing over Large Language Models
%A Liu, Xiliang
%A Xie, Zhiwen
%A Wong, Derek F.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F liu-etal-2026-trace-fine
%X Knowledge editing algorithms have emerged as an efficient paradigm for updating parametric facts in Large Language Models (LLMs) without full retraining. However, existing benchmarks primarily focus on isolated, static facts. While a few temporal datasets exist, they are frequently bottlenecked by coarse temporal granularity, severe relation imbalance, and a critical lack of a priori knowledge validation, which can conflate inherent model deficits with editing failures. To address these structural limitations, we introduce TRACE, a fine-grained Temporal Reasoning And Chronological Editing benchmark. Using exact-match a priori probing, TRACE dynamically constructs model-specific, non-mutually exclusive chronological event chains. Featuring over 16,000 customized test cases across two distinct operational setups (Modify and Insert), TRACE provides a comprehensive 7-dimensional metric matrix. It extends simple fact recall with relation-constrained counterfactual injection and sequential temporal logic probes that test timeline integrity. Our evaluation of 6 representative baselines (FT, IKE, ROME, GRACE, LoRA, WISE) on Llama-3.2-3B and GPT-J-6B identifies widespread temporal interference in the studied settings: editing a single timestamp often sharply degrades recall of adjacent historical and future facts. The consistently weak bidirectional inference after editing further suggests that the evaluated methods tend to introduce shallow, syntax-sensitive patches rather than integrate the edit into a chronological network. Our code, the EasyEdit snapshot used for the experiments, and the benchmark are publicly available.
%U https://aclanthology.org/2026.findings-emnlp.1045/
%P 22130-22143
Markdown (Informal)
[TRACE: A Fine-Grained Benchmark for Temporal Reasoning and Chronological Knowledge Editing over Large Language Models](https://aclanthology.org/2026.findings-emnlp.1045/) (Liu et al., Findings 2026)
ACL