paper-with-me

Papers

Do Large Language Models Solve ARC Visual Analogies Like People Do?

2024-03-13 · Gustaw Opiełka, Hannes Rosenbusch, Veerle Vijverberg, Claire E. Stevenson

The Abstraction Reasoning Corpus (ARC) is a visual analogical reasoning test designed for humans and machines (Chollet, 2019). We compared human and large language model (LLM) performance on a new child-friendly set of ARC items. Results show that both children and adults outperform most LLMs on these tasks. Error analysis revealed a similar "fallback" solution strategy in LLMs and young children, where part of the analogy is simply copied. In addition, we found two other error types, one based on seemingly grasping key concepts (e.g., Inside-Outside) and the other based on simple combinations of analogy input matrices. On the whole, "concept" errors were more common in humans, and "matrix" errors were more common in LLMs. This study sheds new light on LLM reasoning ability and the extent to which we can use error analyses and comparisons with human development to understand how LLMs solve visual analogies.

📄 PDF Abstract BibTeX arXiv:2403.09734

Code (1)

cstevenson-uva/kidsarc 공식 구현

Tasks

ARCLanguage ModelingLanguage ModellingLarge Language ModelVisual Analogies

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Can Large Language Models generalize analogy solving like people can?

2024-11-04 · Claire E. Stevenson, Alexandra Pafford, Han L. J. van der Maas, Melanie Mitchell

When we solve an analogy we transfer information from a known context to a new one through abstract rules and relational similarity. In people, the ability to solve analogies such as "body : feet :: table : ?" emerges in…

Do large language models solve verbal analogies like children do?

2023-10-31 · Claire E. Stevenson, Mathilde ter Veen, Rochelle Choenni, Han L. J. van der Maas 외

Analogy-making lies at the heart of human cognition. Adults solve analogies such as \textit{Horse belongs to stable like chicken belongs to ...?} by mapping relations (\textit{kept in}) and answering \textit{chicken coop…

KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting

2024-12-01 · Thilini Wijesiriwardene, Ruwan Wickramarachchi, Sreeram Vennam, Vinija Jain 외

Making analogies is fundamental to cognition. Proportional analogies, which consist of four terms, are often used to assess linguistic and cognitive abilities. For instance, completing analogies like "Oxygen is to Gas as…

Multiple-choiceMultiple Choice Question Answering (MCQA)Question Answering

VASR: Visual Analogies of Situation Recognition

2022-12-08 · Yonatan Bitton, Ron Yosef, Eli Strugo, Dafna Shahaf 외

A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations. We introduce a novel task, Visual Analogies of Situation Recognition, adapting…

Common Sense ReasoningTripletVisual AnalogiesVisual Commonsense Reasoning+1

Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method

2023-11-14 · Luca H. Thoms, Karel A. Veldkamp, Hannes Rosenbusch, Claire E. Stevenson

Analogical reasoning derives information from known relations and generalizes this information to similar yet unfamiliar situations. One of the first generalized ways in which deep learning models were able to solve verb…

ARCDimensionality ReductionVisual AnalogiesVisual Reasoning+1