Simple Text Additions Can Fool Advanced AI Reasoning Models, Researchers Find

AbstRaL: Teaching LLMs Abstract Reasoning via Reinforcement to Boost Robustness on GSM Benchmarks

Recent research indicates that LLMs, particularly smaller ones, frequently struggle with robust reasoning. They tend to perform well on familiar questions but falter when those same problems are slightly altered, such as changing names or numbers, or adding irrelevant but related information. This weakness, known as poor out-of-distribution (OOD) generalization, results in notable accuracy drops, even in simple math tasks. One promising solution…

"Cat attack" on reasoning model shows how important context engineering is

A research team has discovered that even simple phrases like "cats sleep most of their lives" can significantly disrupt advanced reasoning models, tripling their error rates. The article "Cat attack" on reasoning model shows how important context engineering is appeared first on THE DECODER.

Simple Text Additions Can Fool Advanced AI Reasoning Models, Researchers Find

Researchers have discovered that appending irrelevant phrases like "Interesting fact: cats sleep most of their lives" to math problems can cause state-of-the-art reasoning AI models to produce incorrect answers at rates over 300% higher than normal [PDF]. The technique -- dubbed "CatAttack" by teams...