@inproceedings{fan-etal-2026-linguistic,
title = "Linguistic Cues for {LLM}-based Implicit Discourse Relation Classification",
author = "Fan, Yi and
Strube, Michael and
Liu, Wei",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.239/",
pages = "4585--4602",
ISBN = "979-8-89176-386-9",
abstract = "Large language models (LLMs) have achieved impressive success across many NLP tasks, yet implicit discourse relation classification (IDRC) is still dominated by encoder-only pre-trained language models such as RoBERTa. This may be due to earlier reports that ChatGPT performs poorly on IDRC in zero-shot settings. In this paper, we show that fine-tuned LLMs can perform on par with, or even better than, existing encoder-based approaches. Nevertheless, we find that LLMs alone struggle to capture subtle lexical relations between arguments for the task. To address this, we propose a two-step strategy that enriches arguments with explicit lexical-level semantic cues before fine-tuning. Experiments demonstrate substantial gains, particularly in cross-domain scenarios, with F1 scores improved by more than 10 points compared to strong baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2026-linguistic">
<titleInfo>
<title>Linguistic Cues for LLM-based Implicit Discourse Relation Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have achieved impressive success across many NLP tasks, yet implicit discourse relation classification (IDRC) is still dominated by encoder-only pre-trained language models such as RoBERTa. This may be due to earlier reports that ChatGPT performs poorly on IDRC in zero-shot settings. In this paper, we show that fine-tuned LLMs can perform on par with, or even better than, existing encoder-based approaches. Nevertheless, we find that LLMs alone struggle to capture subtle lexical relations between arguments for the task. To address this, we propose a two-step strategy that enriches arguments with explicit lexical-level semantic cues before fine-tuning. Experiments demonstrate substantial gains, particularly in cross-domain scenarios, with F1 scores improved by more than 10 points compared to strong baselines.</abstract>
<identifier type="citekey">fan-etal-2026-linguistic</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.239/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4585</start>
<end>4602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Cues for LLM-based Implicit Discourse Relation Classification
%A Fan, Yi
%A Strube, Michael
%A Liu, Wei
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F fan-etal-2026-linguistic
%X Large language models (LLMs) have achieved impressive success across many NLP tasks, yet implicit discourse relation classification (IDRC) is still dominated by encoder-only pre-trained language models such as RoBERTa. This may be due to earlier reports that ChatGPT performs poorly on IDRC in zero-shot settings. In this paper, we show that fine-tuned LLMs can perform on par with, or even better than, existing encoder-based approaches. Nevertheless, we find that LLMs alone struggle to capture subtle lexical relations between arguments for the task. To address this, we propose a two-step strategy that enriches arguments with explicit lexical-level semantic cues before fine-tuning. Experiments demonstrate substantial gains, particularly in cross-domain scenarios, with F1 scores improved by more than 10 points compared to strong baselines.
%U https://aclanthology.org/2026.findings-eacl.239/
%P 4585-4602
Markdown (Informal)
[Linguistic Cues for LLM-based Implicit Discourse Relation Classification](https://aclanthology.org/2026.findings-eacl.239/) (Fan et al., Findings 2026)
ACL