Why Someone Asked "Why": Foil Inference in Human and LLM Question Interpretation

2026-05-06

AI Summary

This study investigates how humans infer implicit contrastive alternatives—so-called foils—in unarticulated “why” questions and evaluates the performance of large language models (LLMs) on such contrastive reasoning tasks. Combining behavioral experiments with computational modeling, the research directly compares human participants and multiple LLMs in foil selection. The findings reveal, for the first time, that human foil choices are primarily driven by post-hoc expectations about what could have happened otherwise. Although LLMs can produce foil judgments resembling those of humans, their selections show a marked inconsistency with their own expectation-based predictions, exposing an internal misalignment in their contrastive reasoning mechanisms. This discrepancy underscores a critical limitation in current LLMs’ ability to grasp the implicit contrastive structure underlying causal explanations.

Abstract

Explanations are inherently contrastive: E happened rather than E' because of C rather than C'. However, these contrasts, or "foils", are rarely mentioned explicitly but have to be inferred in context. Here, we investigate how people select the intended foil E' of a why-question. Participants read vignettes and judged, for each foil, their prior expectation (what will happen next), closeness (what is most similar to what happened), and hindsight expectation (what could have happened instead), as well as which foil they thought the question asker had in mind when they asked the why-question. We found that foil selections were best predicted by hindsight expectation judgments. This suggests that people infer the foil by considering what a question asker finds surprising after the outcome occurred. Since correct foil selection is relevant not only in human-human interaction but also increasingly in dialogues with large language models, we investigated their performance on the same task. The coupling between LLMs' explicit expectation judgments and their foil selections is inconsistent.

Problem

• foil inference
• why-questions
• contrastive explanation
• hindsight expectation
• large language models

Innovation

• foil inference
• contrastive explanation
• hindsight expectation
• why-question interpretation
• large language models