paper-with-me

Papers

LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations

2023-05-26 · Yudong Xu, Wenhao Li, Pashootan Vaezipoor, Scott Sanner, Elias B. Khalil

Can a Large Language Model (LLM) solve simple abstract reasoning problems? We explore this broad question through a systematic analysis of GPT on the Abstraction and Reasoning Corpus (ARC), a representative benchmark of abstract reasoning ability from limited examples in which solutions require some "core knowledge" of concepts such as objects, goal states, counting, and basic geometry. GPT-4 solves only 13/50 of the most straightforward ARC tasks when using textual encodings for their two-dimensional input-output grids. Our failure analysis reveals that GPT-4's capacity to identify objects and reason about them is significantly influenced by the sequential nature of the text that represents an object within a text encoding of a task. To test this hypothesis, we design a new benchmark, the 1D-ARC, which consists of one-dimensional (array-like) tasks that are more conducive to GPT-based reasoning, and where it indeed performs better than on the (2D) ARC. To alleviate this issue, we propose an object-based representation that is obtained through an external tool, resulting in nearly doubling the performance on solved ARC tasks and near-perfect scores on the easier 1D-ARC. Although the state-of-the-art GPT-4 is unable to "reason" perfectly within non-language domains such as the 1D-ARC or a simple ARC subset, our study reveals that the use of object-based representations can significantly improve its reasoning ability. Visualizations, GPT logs, and data are available at https://khalil-research.github.io/LLM4ARC.

📄 PDF Abstract BibTeX arXiv:2305.18354

Code (1)

khalil-research/1d-arc

Tasks

ARCLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Test 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Similar Papers 제목 키워드 기반

Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge

2023-10-08 · John Chong Min Tan, Mehul Motani

We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents. Using the flexibility of LLMs to be prompted to do various novel tasks us…

ARCLanguage ModelingLanguage ModellingLarge Language Model+1

Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus

2024-03-18 · Seungpil Lee, Woochang Sim, Donghyeon Shin, Wongyu Seo 외

The existing methods for evaluating the inference abilities of Large Language Models (LLMs) have been predominantly results-centric, making it challenging to assess the inference process comprehensively. We introduce a n…

ARC

Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks

2023-02-16 · Tomer Ullman

Intuitive psychology is a pillar of common-sense reasoning. The replication of this reasoning in machine intelligence is an important stepping-stone on the way to human-like artificial intelligence. Several recent tasks …

Common Sense Reasoning

Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs

2026-04-17 · Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti, Vineeth N Balasubramanian 외 arxiv

Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's E…

Lost in Transmission: When and Why LLMs Fail to Reason Globally

2025-05-13 · Tobias Schnabel, Kiran Tomlinson, Adith Swaminathan, Jennifer Neville

Despite their many successes, transformer-based large language models (LLMs) continue to struggle with tasks that require complex reasoning over large parts of their input. We argue that these failures arise due to capac…