paper-with-me

Papers

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, Jiwon Park, Seokki Lee, Sanha Hwang, Sejin Kim, Sundong Kim

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 novel approach using the Abstraction and Reasoning Corpus (ARC) benchmark to evaluate the inference and contextual understanding abilities of LLMs in a process-centric manner, focusing on three key components from the Language of Thought Hypothesis (LoTH): Logical Coherence, Compositionality, and Productivity. Our carefully designed experiments reveal that while LLMs demonstrate some inference capabilities, they still significantly lag behind human-level reasoning in these three aspects. The main contribution of this paper lies in introducing the LoTH perspective, which provides a method for evaluating the reasoning process that conventional results-oriented approaches fail to capture, thereby offering new insights into the development of human-level reasoning in artificial intelligence systems.

📄 PDF Abstract BibTeX arXiv:2403.11793

Code (1)

GIST-DSLab/ARC_Prompt 공식 구현

Tasks

ARC

Similar Papers 제목 키워드 기반

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models

2025-09-26 · Zhichao Sheng, Shilin Zhou, Chen Gong, Zhenghua Li arxiv

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some met…

FineMath: A Fine-Grained Mathematical Evaluation Benchmark for Chinese Large Language Models

2024-03-12 · Yan Liu, Renren Jin, Ling Shi, Zheng Yao 외

To thoroughly assess the mathematical reasoning abilities of Large Language Models (LLMs), we need to carefully curate evaluation datasets covering diverse mathematical concepts and mathematical problems at different dif…

MathMathematical Reasoning

Reasoning with Latent Thoughts: On the Power of Looped Transformers

2025-02-24 · Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar 외

Large language models have shown remarkable reasoning abilities and scaling laws suggest that large parameter count, especially along the depth axis, is the primary driver. In this work, we make a stronger claim -- many …

Language ModelingLanguage ModellingMathMemorization

Kongzi: A Historical Large Language Model with Fact Enhancement

2025-04-13 · Jiashu Yang, Ningning Wang, Yian Zhao, Chaoran Feng 외

The capabilities of the latest large language models (LLMs) have been extended from pure natural language understanding to complex reasoning tasks. However, current reasoning models often exhibit factual inaccuracies in …

Language ModelingLanguage ModellingLarge Language ModelNatural Language Understanding+1

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

2024-11-09 · Fatemeh Shiri, Xiao-Yu Guo, Mona Golestan Far, Xin Yu 외

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA d…

object-detectionObject DetectionSpatial ReasoningVisual Question Answering (VQA)