Did You Forget What I Asked? Prospective Memory Failures in Large Language Models

TL;DR

This paper investigates how large language models struggle with formatting instructions under multitasking conditions, revealing vulnerabilities and proposing a salience-based intervention to improve compliance.

Contribution

It introduces a cognitive psychology-inspired framework to analyze LLM formatting failures and demonstrates effective strategies to mitigate these issues.

Findings

Compliance drops 2-21% under concurrent tasks

Terminal constraints cause up to 50% compliance degradation

Salience-enhanced formatting restores compliance to 90-100%

Abstract

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled paradigm that combines verifiable formatting constraints with benchmark tasks of increasing complexity. Across three model families and over 8,000 prompts, compliance drops by 2-21% under concurrent task load. Vulnerability is highly type-dependent: terminal constraints (requiring action at the response boundary) degrade most, with drops up to 50%, while avoidance constraints remain comparatively robust. A salience-enhanced format (explicit instruction framing plus a trailing reminder) recovers much of the lost compliance, restoring performance to 90-100% in many settings. Interference is bidirectional: formatting constraints can also reduce task accuracy, with one model's GSM8K accuracy dropping from 93% to 27%. In additional stacking experiments, joint compliance declines sharply as constraints accumulate. All results use deterministic programmatic checkers without an LLM-as-judge component on publicly available datasets.