@inproceedings{orsini-brunato-2026-steering,
title = "Steering Pragmatic Interpretation in {LLM}s: A Diagnostic Evaluation of Few-Shot and Reasoning-Based Prompting for Indirect Speech Acts.",
author = "Orsini, Massimiliano and
Brunato, Dominique",
editor = "Egg, Markus and
Kordoni, Valia",
booktitle = "Proceedings of Learning Non-Literal Expressions with Small Data @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nonliteral-1.2/",
doi = "10.63317/49dfcg89tqms",
pages = "12--20",
abstract = "Pragmatic competence poses a persistent challenge for large language models, as it requires context-dependent inference beyond literal meaning. This study examines whether few-shot prompting can reliably steer LLMs toward appropriate interpretations of indirect speech acts under small-data conditions. Focusing on Italian, we evaluate three LLMs on a small dataset that captures pragmatic ambiguity through graded plausibility judgments. We compare a zero-shot baseline with multiple few-shot prompting configurations that vary in the number and composition of demonstrations, as well as in the presence of explicit pragmatic guidance. Results show that few-shot prompting does not yield robust or monotonic improvements overall. While performance improves substantially for conventionalized indirect speech acts, gains for non-conventionalized indirect speech acts are unstable and limited. In contrast, introducing explicit pragmatic reasoning along with demonstrations through guided chain-of-thought prompting appears more promising. Overall, these findings highlight the limits of example-based steering for pragmatic inference and suggest that explicitly modeling pragmatic reasoning may be a more effective direction in small-data settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="orsini-brunato-2026-steering">
<titleInfo>
<title>Steering Pragmatic Interpretation in LLMs: A Diagnostic Evaluation of Few-Shot and Reasoning-Based Prompting for Indirect Speech Acts.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Massimiliano</namePart>
<namePart type="family">Orsini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Brunato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Egg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valia</namePart>
<namePart type="family">Kordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pragmatic competence poses a persistent challenge for large language models, as it requires context-dependent inference beyond literal meaning. This study examines whether few-shot prompting can reliably steer LLMs toward appropriate interpretations of indirect speech acts under small-data conditions. Focusing on Italian, we evaluate three LLMs on a small dataset that captures pragmatic ambiguity through graded plausibility judgments. We compare a zero-shot baseline with multiple few-shot prompting configurations that vary in the number and composition of demonstrations, as well as in the presence of explicit pragmatic guidance. Results show that few-shot prompting does not yield robust or monotonic improvements overall. While performance improves substantially for conventionalized indirect speech acts, gains for non-conventionalized indirect speech acts are unstable and limited. In contrast, introducing explicit pragmatic reasoning along with demonstrations through guided chain-of-thought prompting appears more promising. Overall, these findings highlight the limits of example-based steering for pragmatic inference and suggest that explicitly modeling pragmatic reasoning may be a more effective direction in small-data settings.</abstract>
<identifier type="citekey">orsini-brunato-2026-steering</identifier>
<identifier type="doi">10.63317/49dfcg89tqms</identifier>
<location>
<url>https://aclanthology.org/2026.nonliteral-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>12</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Steering Pragmatic Interpretation in LLMs: A Diagnostic Evaluation of Few-Shot and Reasoning-Based Prompting for Indirect Speech Acts.
%A Orsini, Massimiliano
%A Brunato, Dominique
%Y Egg, Markus
%Y Kordoni, Valia
%S Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F orsini-brunato-2026-steering
%X Pragmatic competence poses a persistent challenge for large language models, as it requires context-dependent inference beyond literal meaning. This study examines whether few-shot prompting can reliably steer LLMs toward appropriate interpretations of indirect speech acts under small-data conditions. Focusing on Italian, we evaluate three LLMs on a small dataset that captures pragmatic ambiguity through graded plausibility judgments. We compare a zero-shot baseline with multiple few-shot prompting configurations that vary in the number and composition of demonstrations, as well as in the presence of explicit pragmatic guidance. Results show that few-shot prompting does not yield robust or monotonic improvements overall. While performance improves substantially for conventionalized indirect speech acts, gains for non-conventionalized indirect speech acts are unstable and limited. In contrast, introducing explicit pragmatic reasoning along with demonstrations through guided chain-of-thought prompting appears more promising. Overall, these findings highlight the limits of example-based steering for pragmatic inference and suggest that explicitly modeling pragmatic reasoning may be a more effective direction in small-data settings.
%R 10.63317/49dfcg89tqms
%U https://aclanthology.org/2026.nonliteral-1.2/
%U https://doi.org/10.63317/49dfcg89tqms
%P 12-20
Markdown (Informal)
[Steering Pragmatic Interpretation in LLMs: A Diagnostic Evaluation of Few-Shot and Reasoning-Based Prompting for Indirect Speech Acts.](https://aclanthology.org/2026.nonliteral-1.2/) (Orsini & Brunato, NonLiteral 2026)
ACL