The Model Says Walk: Measuring whether LLMs Condition on Hidden Constraints
cs.CL, cs.AI
Submitted: 2026-03-30
Updated: 2026-09-26
Code: https://github.com/yubol-bobo/HiddenConstraintBench
License: http://creativecommons.org/licenses/by/4.0/
The gist: Asked whether to walk or drive to a car wash 50 m away, most language models say walk, forgetting that the car has to be there.
Terminology
Abstract
Asked whether to walk or drive to a car wash 50 m away, most language models say walk, forgetting that the car has to be there. Such failures are usually measured by accuracy on questions where the hidden constraint applies. We show that this is misleading: a model can answer these questions correctly without reasoning about the constraint at all, simply by favoring the cautious option. We instead ask whether a model's decision changes when the constraint is removed. We test this at three levels of control: log-probability sweeps on open-weight models, a 500-prompt stress test, and CORE, a new human-validated benchmark of minimal constraint-present/constraint-absent pairs. The picture is consistent. The constraint nudges decisions rather than governing them. Models still miss presence constraints like the car wash, yet elsewhere they apply constraints that are not there. As a result, standard accuracy flatters all ten models we evaluate and reorders their ranking, and prompting fixes that look effective largely vanish under paired scoring. Claims about hidden-constraint reasoning need paired evidence.
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem
- GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
- Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
- Rethinking Interpretability in the Era of Large Language Models
- Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis
- Will the Real Linda Please Stand up...to Large Language Models? Examining the Representativeness Heuristic in LLMs
- Instruction-Following Evaluation for Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering