Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models

TL;DR

This paper reveals that state-of-the-art large language models, including GPT-4 and Claude 3, fail dramatically on simple reasoning tasks, exposing significant gaps in their generalization and reasoning abilities despite high benchmark scores.

Contribution

The study demonstrates a simple reasoning problem causes major performance breakdowns in SOTA LLMs, challenging current benchmark validity and highlighting the need for improved evaluation methods.

Findings

SOTA models perform poorly on simple common sense math problems

Models exhibit overconfidence and confabulations in incorrect solutions

Standard interventions like chain-of-thought prompting fail to improve reasoning accuracy

Abstract

Large Language Models (LLMs) are often described as instances of foundation models that possess strong generalization obeying scaling laws, and therefore transfer robustly across various conditions in few- or zero-shot manner. Such claims rely on standardized benchmarks that suppose to measure generalization and reasoning, where state-of-the-art (SOTA) models score high. We demonstrate here a dramatic breakdown of generalization and basic reasoning of all SOTA models claiming strong function, including large scale advanced models like GPT-4 or Claude 3 Opus, using a simple, short common sense math problem formulated in concise natural language, easily solvable by humans (AIW problem). The breakdown is dramatic as it manifests on a simple problem in both low average performance and strong performance fluctuations on natural variations in problem template that do not change either problem structure or its difficulty at all. By testing models on further control problems with similar form, we rule out that breakdown might be rooted in minor low-level issues like natural language or numbers parsing. We also observe strong overconfidence in the wrong solutions, expressed in form of plausible sounding explanation-like confabulations. Various standard interventions in an attempt to get the right solution, like chain-of-thought prompting, or urging the models to reconsider the wrong solutions again by multi step re-evaluation, fail. We use these observations to stimulate re-assessment of the capabilities of current generation of LLMs as claimed by standardized benchmarks. Such re-assessment also requires common action to create standardized benchmarks that would allow proper detection of such deficits in generalization and reasoning that obviously remain undiscovered by current state-of-the-art evaluation procedures, where SOTA LLMs manage to score high. Code: https://github.com/LAION-AI/AIW