Saved in:
Bibliographic Details
Main Authors: Bila, Natalia, Naszádi, Kata, Mayn, Alexandra, Monz, Christof
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19997
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917354824269824
author Bila, Natalia
Naszádi, Kata
Mayn, Alexandra
Monz, Christof
author_facet Bila, Natalia
Naszádi, Kata
Mayn, Alexandra
Monz, Christof
contents We investigate the separation of literal interpretation from contextual inference in a collaborative block-building task where a builder must resolve underspecified instructions using contextual inferences. Building on an existing two-speaker psycholinguistic paradigm -- which contrasts a pragmatically cooperative speaker with one who is only literally reliable -- we introduce Build What I Mean (BWIM), an interactive benchmark for contextual meaning construction. In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost. Evaluating several state-of-the-art LLMs, we find a dissociation between judgment and action: while models detect speaker unreliability in explicit confidence ratings, they fail to exploit this information to guide efficient clarification behavior. Instead, we observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19997
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When Contextual Inference Fails: Cancelability in Interactive Instruction Following
Bila, Natalia
Naszádi, Kata
Mayn, Alexandra
Monz, Christof
Computation and Language
We investigate the separation of literal interpretation from contextual inference in a collaborative block-building task where a builder must resolve underspecified instructions using contextual inferences. Building on an existing two-speaker psycholinguistic paradigm -- which contrasts a pragmatically cooperative speaker with one who is only literally reliable -- we introduce Build What I Mean (BWIM), an interactive benchmark for contextual meaning construction. In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost. Evaluating several state-of-the-art LLMs, we find a dissociation between judgment and action: while models detect speaker unreliability in explicit confidence ratings, they fail to exploit this information to guide efficient clarification behavior. Instead, we observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.
title When Contextual Inference Fails: Cancelability in Interactive Instruction Following
topic Computation and Language
url https://arxiv.org/abs/2603.19997